aysin commited on
Commit
6ca0a4b
·
verified ·
1 Parent(s): ff29ace

Add files using upload-large-folder tool

Browse files
Files changed (50) hide show
  1. hopper_medium_expert_sparse/mbpo_based/kde/seed_42_0329_235228_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth +0 -0
  2. hopper_medium_expert_sparse/mbpo_based/neuralODE/seed_123_0329_154924_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth +0 -0
  3. hopper_medium_expert_sparse/mbpo_based/realnvp/seed_123_0329_125153_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth +0 -0
  4. hopper_medium_expert_sparse/mobile_based/diffusion/seed_123&timestamp_26-0317-191425/record/consoleout_backup.txt +0 -0
  5. hopper_medium_expert_sparse/mobile_based/diffusion/seed_123&timestamp_26-0317-191425/record/dynamics_training_progress.csv +0 -0
  6. hopper_medium_expert_sparse/mobile_based/diffusion/seed_123&timestamp_26-0317-191425/record/hyper_param.json +1 -0
  7. hopper_medium_expert_sparse/mobile_based/diffusion/seed_123&timestamp_26-0317-191425/record/policy_training_progress.csv +61 -0
  8. hopper_medium_expert_sparse/mobile_based/diffusion/seed_42&timestamp_26-0317-001620/record/consoleout_backup.txt +0 -0
  9. hopper_medium_expert_sparse/mobile_based/diffusion/seed_42&timestamp_26-0317-001620/record/dynamics_training_progress.csv +0 -0
  10. hopper_medium_expert_sparse/mobile_based/diffusion/seed_42&timestamp_26-0317-001620/record/hyper_param.json +1 -0
  11. hopper_medium_expert_sparse/mobile_based/diffusion/seed_456&timestamp_26-0318-182716/record/consoleout_backup.txt +0 -0
  12. hopper_medium_expert_sparse/mobile_based/diffusion/seed_456&timestamp_26-0318-182716/record/dynamics_training_progress.csv +0 -0
  13. hopper_medium_expert_sparse/mobile_based/diffusion/seed_456&timestamp_26-0318-182716/record/hyper_param.json +1 -0
  14. hopper_medium_expert_sparse/mobile_based/diffusion/seed_456&timestamp_26-0318-182716/record/policy_training_progress.csv +61 -0
  15. hopper_medium_expert_sparse/mobile_based/kde/seed_123&timestamp_26-0505-201136/record/consoleout_backup.txt +39 -0
  16. hopper_medium_expert_sparse/mobile_based/kde/seed_123&timestamp_26-0505-201136/record/dynamics_training_progress.csv +0 -0
  17. hopper_medium_expert_sparse/mobile_based/kde/seed_123&timestamp_26-0505-201136/record/hyper_param.json +1 -0
  18. hopper_medium_expert_sparse/mobile_based/kde/seed_123&timestamp_26-0505-201136/record/policy_training_progress.csv +0 -0
  19. hopper_medium_expert_sparse/mobile_based/kde/seed_42&timestamp_26-0505-202702/record/consoleout_backup.txt +0 -0
  20. hopper_medium_expert_sparse/mobile_based/kde/seed_42&timestamp_26-0505-202702/record/dynamics_training_progress.csv +0 -0
  21. hopper_medium_expert_sparse/mobile_based/kde/seed_42&timestamp_26-0505-202702/record/hyper_param.json +1 -0
  22. hopper_medium_expert_sparse/mobile_based/kde/seed_42&timestamp_26-0505-202702/record/policy_training_progress.csv +61 -0
  23. hopper_medium_expert_sparse/mobile_based/kde/seed_456&timestamp_26-0505-202659/record/consoleout_backup.txt +0 -0
  24. hopper_medium_expert_sparse/mobile_based/kde/seed_456&timestamp_26-0505-202659/record/dynamics_training_progress.csv +0 -0
  25. hopper_medium_expert_sparse/mobile_based/kde/seed_456&timestamp_26-0505-202659/record/hyper_param.json +1 -0
  26. hopper_medium_expert_sparse/mobile_based/kde/seed_456&timestamp_26-0505-202659/record/policy_training_progress.csv +61 -0
  27. hopper_medium_expert_sparse/mobile_based/neuralODE/seed_123&timestamp_26-0506-193304/record/consoleout_backup.txt +0 -0
  28. hopper_medium_expert_sparse/mobile_based/neuralODE/seed_123&timestamp_26-0506-193304/record/dynamics_training_progress.csv +0 -0
  29. hopper_medium_expert_sparse/mobile_based/neuralODE/seed_123&timestamp_26-0506-193304/record/hyper_param.json +1 -0
  30. hopper_medium_expert_sparse/mobile_based/neuralODE/seed_123&timestamp_26-0506-193304/record/policy_training_progress.csv +61 -0
  31. hopper_medium_expert_sparse/mobile_based/neuralODE/seed_42&timestamp_26-0506-193304/record/consoleout_backup.txt +0 -0
  32. hopper_medium_expert_sparse/mobile_based/neuralODE/seed_42&timestamp_26-0506-193304/record/dynamics_training_progress.csv +0 -0
  33. hopper_medium_expert_sparse/mobile_based/neuralODE/seed_42&timestamp_26-0506-193304/record/hyper_param.json +1 -0
  34. hopper_medium_expert_sparse/mobile_based/neuralODE/seed_42&timestamp_26-0506-193304/record/policy_training_progress.csv +61 -0
  35. hopper_medium_expert_sparse/mobile_based/neuralODE/seed_456&timestamp_26-0506-193304/record/consoleout_backup.txt +0 -0
  36. hopper_medium_expert_sparse/mobile_based/neuralODE/seed_456&timestamp_26-0506-193304/record/dynamics_training_progress.csv +0 -0
  37. hopper_medium_expert_sparse/mobile_based/neuralODE/seed_456&timestamp_26-0506-193304/record/hyper_param.json +1 -0
  38. hopper_medium_expert_sparse/mobile_based/neuralODE/seed_456&timestamp_26-0506-193304/record/policy_training_progress.csv +61 -0
  39. hopper_medium_expert_sparse/mobile_based/realnvp/seed_123&timestamp_26-0318-103140/record/consoleout_backup.txt +0 -0
  40. hopper_medium_expert_sparse/mobile_based/realnvp/seed_123&timestamp_26-0318-103140/record/dynamics_training_progress.csv +0 -0
  41. hopper_medium_expert_sparse/mobile_based/realnvp/seed_123&timestamp_26-0318-103140/record/hyper_param.json +1 -0
  42. hopper_medium_expert_sparse/mobile_based/realnvp/seed_123&timestamp_26-0318-103140/record/policy_training_progress.csv +61 -0
  43. hopper_medium_expert_sparse/mobile_based/realnvp/seed_42&timestamp_26-0317-002436/record/consoleout_backup.txt +0 -0
  44. hopper_medium_expert_sparse/mobile_based/realnvp/seed_42&timestamp_26-0317-002436/record/dynamics_training_progress.csv +0 -0
  45. hopper_medium_expert_sparse/mobile_based/realnvp/seed_42&timestamp_26-0317-002436/record/hyper_param.json +1 -0
  46. hopper_medium_expert_sparse/mobile_based/realnvp/seed_42&timestamp_26-0317-002436/record/policy_training_progress.csv +61 -0
  47. hopper_medium_expert_sparse/mobile_based/realnvp/seed_456&timestamp_26-0319-223848/record/consoleout_backup.txt +0 -0
  48. hopper_medium_expert_sparse/mobile_based/realnvp/seed_456&timestamp_26-0319-223848/record/dynamics_training_progress.csv +0 -0
  49. hopper_medium_expert_sparse/mobile_based/realnvp/seed_456&timestamp_26-0319-223848/record/hyper_param.json +1 -0
  50. hopper_medium_expert_sparse/mobile_based/realnvp/seed_456&timestamp_26-0319-223848/record/policy_training_progress.csv +61 -0
hopper_medium_expert_sparse/mbpo_based/kde/seed_42_0329_235228_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth ADDED
File without changes
hopper_medium_expert_sparse/mbpo_based/neuralODE/seed_123_0329_154924_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth ADDED
File without changes
hopper_medium_expert_sparse/mbpo_based/realnvp/seed_123_0329_125153_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth ADDED
File without changes
hopper_medium_expert_sparse/mobile_based/diffusion/seed_123&timestamp_26-0317-191425/record/consoleout_backup.txt ADDED
The diff for this file is too large to render. See raw diff
 
hopper_medium_expert_sparse/mobile_based/diffusion/seed_123&timestamp_26-0317-191425/record/dynamics_training_progress.csv ADDED
File without changes
hopper_medium_expert_sparse/mobile_based/diffusion/seed_123&timestamp_26-0317-191425/record/hyper_param.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"config": "config_gormpo/hopper_medium_expert_7_diffusion.yaml", "algo_name": "mobile_gormpo", "task": "hopper-medium-expert-v2", "seed": 123, "device": "cuda:0", "dataset_path": "/public/d4rl/sparse_datasets/hopper_medium_expert_sparse_78.pkl", "dynamics_path": "log/hopper-medium-expert-v2/seed_123&timestamp_26-0112-030632/model", "reward_penalty_coef": 0.5, "classifier_model_name": "/public/gormpo/models/hopper_medium_expert_sparse_3/diffusion/checkpoint.pt", "use_wandb": true, "wandb_project": "mobile-gormpo", "wandb_entity": null, "domain": "gym", "actor_lr": 0.0001, "critic_lr": 0.0003, "hidden_dims": [256, 256], "gamma": 0.99, "tau": 0.005, "alpha": 0.2, "auto_alpha": true, "target_entropy": -3.0, "alpha_lr": 0.0001, "deterministic_backup": true, "max_q_backup": false, "norm_reward": false, "num_q_ensemble": 2, "dynamics_lr": 0.001, "dynamics_max_epochs": null, "max_epochs_since_update": 5, "dynamics_hidden_dims": [200, 200, 200, 200], "dynamics_weight_decay": [2.5e-05, 5e-05, 7.5e-05, 7.5e-05, 0.0001], "n_ensemble": 7, "n_elites": 5, "rollout_freq": 1000, "rollout_batch_size": 50000, "rollout_length": 5, "penalty_coef": 1.5, "num_samples": 10, "model_retain_epochs": 5, "real_ratio": 0.05, "load_dynamics_path": null, "epoch": 3000, "step_per_epoch": 1000, "eval_episodes": 100, "batch_size": 256, "lr_scheduler": true, "density_model": "diffusion", "data_path": "/public/d4rl/sparse_datasets/hopper_medium_expert_sparse_78.pkl", "penalty_type": "tanh", "obs_shape": [11], "action_dim": 3.0, "max_action": 1.0, "classifier_type": "diffusion"}
hopper_medium_expert_sparse/mobile_based/diffusion/seed_123&timestamp_26-0317-191425/record/policy_training_progress.csv ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ alpha,eval/episode_length,eval/episode_length_std,eval/normalized_episode_reward,eval/normalized_episode_reward_std,loss/actor,loss/alpha,loss/critic,penalty/lcb_mean,penalty/lcb_std,rollout_info/dynamics_penalty_mean,rollout_info/dynamics_penalty_std,rollout_info/num_transitions,rollout_info/reward_mean,timestep
2
+ 0.24259124923542041,52.46,2.1280037593951753,3.4796522773670278,0.7573975148251866,-316.41378168730733,-0.9907932005336089,17.478537819971997,0.4142775725945903,0.5804586112804306,1.0,0.0,249265.40000000002,2.9896520799634367,50000
3
+ 0.09308433767512528,38.39,7.177597090949031,2.4838349074687454,1.156987394576546,-468.7187575207433,-0.030688578566722333,19.921801813220714,0.4234062660270956,0.7218016848266077,1.0,0.0,249307.38,2.9659305719921054,100000
4
+ 0.07518011294469165,55.36,0.6858571279792898,3.7957075497735575,0.6668094747519254,-357.30098748779153,-0.031404785896316366,10.2195722613502,0.33683345965921996,0.5326865479224905,1.0,0.0,249319.3199999999,2.9129267478589713,150000
5
+ 0.0499392998716978,67.06,0.8345058418010028,4.737522468788382,0.6791778880069628,-288.8195568499687,-0.08608888476688493,6.754143402655184,0.23073574388638382,0.3800188562574951,1.0,0.0,249311.13999999998,2.8829311331235252,200000
6
+ 0.03312957703072656,27.46,55.552393287778344,2.2888615370426475,6.667788703631623,-262.9376115582218,0.0027995348361507908,5.340211080365153,0.18551190823033575,0.33514455231695756,1.0,0.0,249308.99999999997,2.855051729411924,250000
7
+ 0.02874526993863301,47.3,1.063014581273465,3.0280250240925155,0.7033554046976022,-259.6707549609422,-0.04651191448844946,4.9445182527578195,0.1750668350610142,0.3272150067184877,1.0,0.0,249319.90000000002,2.8469651003367558,300000
8
+ 0.027287565084285988,230.94,1.008166652890285,22.40290141775969,0.7641885503268165,-259.4889516253632,0.009337002243026927,5.104104828716545,0.1781471608808622,0.3404923149967243,1.0,0.0,249322.42,2.840342010817694,350000
9
+ 0.02563094361606998,825.4,176.1272835196183,89.25918666234551,20.041851763621697,-260.30265586761624,0.008048152641355976,4.521713854544204,0.17677805714473088,0.3346300900004844,1.0,0.0,249319.61999999994,2.8282540601104467,400000
10
+ 0.026843010434955406,653.65,239.80047435315888,72.3639511471427,28.0891431039775,-260.9212060754427,0.008558515350147967,4.710605764025346,0.18394219686061292,0.35112192713469353,1.0,0.0,249314.95999999993,2.830556506293962,450000
11
+ 0.026360266502127198,951.73,119.91170543362313,104.09225399244202,14.16983204423837,-262.8465160913115,0.014322214477509289,4.991554422422646,0.18714038818046594,0.3562326966659759,1.0,0.0,249326.07999999993,2.8303326299932516,500000
12
+ 0.02628742178555566,136.6,0.7211102550927979,11.339648348653867,0.7238027003150772,-262.12660919403794,0.016037292035370996,4.430486014436476,0.1899536716574438,0.3630019181597264,1.0,0.0,249324.19999999995,2.8302259725409478,550000
13
+ 0.025827377317696836,316.19,209.01022439105697,32.75030850670754,24.87873653583935,-262.86615310516254,-0.006458335118591822,3.055130809078239,0.19039492102011984,0.3641973292721835,1.0,0.0,249314.58000000005,2.8294217302949454,600000
14
+ 0.026074443726725894,34.14,2.2672450242530027,2.0804947831011202,0.7621045458267197,-262.05970286071295,0.035627837132252746,4.203216265325505,0.1925119403323541,0.3619333092410825,1.0,0.0,249332.63999999998,2.8273267010828023,650000
15
+ 0.028403124623931825,102.85,1.6271140095272978,8.81291695833687,0.807727263920331,-262.3606375866742,0.021837788360044463,6.917838511830475,0.19643485932648194,0.370575742426068,1.0,0.0,249315.36000000004,2.8346159346969695,700000
16
+ 0.02604865023732194,103.22,11.912665528755518,8.892154414356543,2.2780889267008977,-262.3486896453853,-0.003401023259609987,3.5724394365626626,0.1977214533117404,0.3764119946552851,1.0,0.0,249337.73999999996,2.8367872119723883,750000
17
+ 0.025168123111575555,498.71,190.29131850927936,52.639473485262,22.60316414499447,-262.65820299896666,0.0014903027562051965,3.200412311779873,0.19847998186454083,0.3849262223963422,1.0,0.0,249324.82,2.837288863956501,800000
18
+ 0.02875282132796969,104.79,1.070467187726929,8.736385537029847,0.7513211936682607,-263.6944767547564,0.10845341900124929,7.298593843318279,0.20431771921545222,0.39945293869346227,1.0,0.0,249313.58000000002,2.840849958853755,850000
19
+ 0.024108721732236955,226.27,116.71733847205394,21.604315453471408,13.899614315436509,-263.2631936376947,-0.005614523120243433,3.9459819609290103,0.19371356218501964,0.382373312319071,1.0,0.0,249310.0400000001,2.841650118823153,900000
20
+ 0.02314347491156299,1000.0,0.0,112.64577181313386,1.140184768820991,-263.34637530913835,0.02172264554500588,3.410531684627546,0.19339691463530145,0.38560815804123894,1.0,0.0,249325.98,2.839477752787111,950000
21
+ 0.02223825107604279,858.77,228.94994452936646,96.92101661778894,27.025215361188557,-263.8865391616767,-0.02806123621471278,2.9921882911354456,0.1942211026948671,0.39167284437775707,1.0,0.0,249321.52,2.8350139938507097,1000000
22
+ 0.021471234300472042,751.13,298.2947084679848,84.06741695904066,35.737022199028985,-264.5140883367906,-0.0010488831074909203,2.7923726355439036,0.19429323708176813,0.3915883216877249,1.0,0.0,249318.27999999997,2.8365459663573294,1050000
23
+ 0.02160308951955328,710.96,233.35710488433816,82.9719288677245,26.347760579790986,-264.85710081725773,0.022106919013931726,3.6313345722323755,0.1948774642583728,0.39523217692792684,1.0,0.0,249310.40000000002,2.838435352090448,1100000
24
+ 0.02094985288329408,971.56,108.13198601708932,110.58345858957448,12.576397981272555,-264.9621152478017,-0.0014776624544712122,2.738420088614808,0.19391480915442116,0.39199709521338,1.0,0.0,249327.84,2.8372121969507758,1150000
25
+ 0.022221025132536917,1000.0,0.0,112.85290961466634,0.7244391364570498,-264.53051376159533,0.005334775384068867,3.9784788728052076,0.19975625514343506,0.40279383660346263,1.0,0.0,249329.09999999998,2.840044095910493,1200000
26
+ 0.02161616544980556,998.0,19.8997487421324,112.79721902145963,2.539226907043465,-264.0087083007827,0.011698654758706607,3.3439349449461813,0.20285138186276105,0.41490997131988705,1.0,0.0,249312.31999999992,2.834772975449616,1250000
27
+ 0.021691714195273812,1000.0,0.0,112.82632765090777,0.8678264383958899,-263.76746940551845,0.0006333856937290304,3.8531993240940863,0.20351687683492667,0.4163687148040495,1.0,0.0,249330.14000000004,2.836034325170679,1300000
28
+ 0.02103164238270374,1000.0,0.0,112.31461893217383,1.1939436266807317,-263.4042464328,-0.005340631298646476,2.97269783563019,0.20349955778286027,0.42088369548797805,1.0,0.0,249308.67999999996,2.8368523437919646,1350000
29
+ 0.021105194823071053,734.68,331.82109275933624,81.77033339506458,39.64852603880182,-263.2108670593334,-0.010097727501243353,3.5106096499585706,0.2028548303912581,0.42871887653559576,1.0,0.0,249329.0,2.8371522580149877,1400000
30
+ 0.021439492515809365,946.2,119.31906804865685,108.36533054710236,14.39561936833416,-263.3505860235586,0.024437146439850534,2.9170911227911933,0.20493960107609752,0.42838461529820937,1.0,0.0,249318.65999999997,2.8347310822423717,1450000
31
+ 0.021838954847417758,193.02,1.3489254983133798,18.525763393505937,0.782399102618566,-262.7024997348049,0.0009789635082331025,4.152132252318866,0.2041722768823802,0.43400349077731704,1.0,0.0,249323.91999999993,2.8358248080635775,1500000
32
+ 0.0205632904895022,1000.0,0.0,112.62631400375243,0.8023329507631192,-263.6764285345419,-0.0004749199671296413,3.0952947198111214,0.20212352602258382,0.43038956215232765,1.0,0.0,249316.55999999994,2.835616513368918,1550000
33
+ 0.020923914131485068,976.56,82.69973639619415,111.3501723732933,10.166549265697808,-263.7945922567726,0.009165617556124824,3.0333349943661476,0.20197473706185756,0.43408828443244507,1.0,0.0,249316.37999999998,2.8350915769657785,1600000
34
+ 0.02064971969980782,1000.0,0.0,112.56027087553888,0.7868393800718474,-264.0085326205459,0.0020310872136055837,3.054653370361301,0.2038549198715394,0.42956240633994897,1.0,0.0,249324.68,2.8343482121689756,1650000
35
+ 0.021146714676320556,1000.0,0.0,112.70570690720632,0.8268046379783404,-263.75268219207567,0.0158134118159861,2.8057584395861794,0.2057108344352267,0.4339167393109202,1.0,0.0,249307.00000000006,2.835738157181241,1700000
36
+ 0.02085276934113346,995.6,30.759388810572943,111.972255800402,4.218373677273792,-263.9615962750239,-0.013439251172617442,3.034825209483501,0.20257055986240252,0.4322112891745647,1.0,0.0,249323.98,2.836058396443542,1750000
37
+ 0.019868074633293088,995.38,32.35514796751825,112.8077906991299,4.214717748296624,-264.00146112762263,-0.005003491582572415,2.934294062210304,0.2017015902109449,0.43410928661048226,1.0,0.0,249318.85999999996,2.8347612839921816,1800000
38
+ 0.019690088802613092,183.61,169.03673535654903,17.320865303821943,20.405223652389452,-264.1646427688531,-0.0009565613818914996,2.8116341583037374,0.20316318178891737,0.43415788538962635,1.0,0.0,249324.79999999993,2.8350188750919356,1850000
39
+ 0.020390913697481063,1000.0,0.0,112.55849781921523,1.0013636748886758,-264.1301975952163,0.011930296053960784,3.210206161428667,0.2034881492312259,0.43240689647897895,1.0,0.0,249312.70000000004,2.836772762490458,1900000
40
+ 0.018985050977655057,1000.0,0.0,112.71476230336579,0.8792720919262208,-265.1434742352302,0.012398427265360858,2.8930510398626272,0.19721236737593784,0.4184522199738001,1.0,0.0,249316.6,2.833176020237847,1950000
41
+ 0.019735354192182322,345.66,331.41355494306504,36.42557070761437,39.23303398611363,-264.85300082275825,-0.01904591439999607,2.8596879655921605,0.20165458324447208,0.4236563787838775,1.0,0.0,249329.2799999999,2.834449040860213,2000000
42
+ 0.019695518280677577,998.61,13.830325375782015,113.9568271316833,2.176803303019905,-264.8392685610941,0.0006428555489333543,3.2691489409941528,0.20301627261727825,0.42707353522688357,1.0,0.0,249320.21999999997,2.8386729229353374,2050000
43
+ 0.01873484302144516,994.08,41.44096523972385,112.50947724150906,5.3154427702847995,-264.8919157684294,-0.0008947350142153575,2.5118161889309,0.19957283042982144,0.4166002747303235,1.0,0.0,249323.75999999992,2.833733756259877,2100000
44
+ 0.018671778568438893,1000.0,0.0,112.58591743433372,0.8495511219128918,-265.2285871795681,0.004292291607447136,2.305228708542625,0.2003026164320095,0.41824737611293944,1.0,0.0,249320.18,2.8335822273450813,2150000
45
+ 0.0188914923430608,829.7,247.46100702939037,93.87086684072227,29.828460341635754,-264.57726048034846,0.002428072425127111,2.3681124507921467,0.20240782355070155,0.42107373172104545,1.0,0.0,249328.33999999994,2.8360635485467047,2200000
46
+ 0.01882738319724766,924.95,182.69681852730767,104.60767390773609,22.193353312300555,-264.5402311950665,0.0033654400517049037,2.368809686744228,0.19887170253947528,0.4093881664320846,1.0,0.0,249317.35999999996,2.8341673144328015,2250000
47
+ 0.01833288361392935,616.39,383.5006621897803,68.0265582066095,45.79636822923941,-264.730434383846,-0.0003786409064381612,2.402921569085733,0.19727021992146895,0.4131808749616172,1.0,0.0,249319.08,2.8346538771089183,2300000
48
+ 0.01851751285042606,181.99,2.451509738916001,16.999903196436662,0.9244840233457643,-264.3676663803071,-0.014583082658052422,2.32044427067697,0.19952010024562375,0.41089801338940773,1.0,0.0,249311.54,2.834760816917238,2350000
49
+ 0.017934288626015187,196.81,5.266298510339117,18.763025038255094,1.2705748553983105,-264.77605434051765,0.00450208193510777,2.15837180482565,0.20051651646256413,0.4164577171418067,1.0,0.0,249320.26000000004,2.8343268055989754,2400000
50
+ 0.01756045855451369,1000.0,0.0,113.00868826656507,0.9757400624664205,-264.53175671692173,0.003212293625697516,2.3211556269276494,0.20058698398694416,0.4186761819854384,1.0,0.0,249329.66000000003,2.8352856958444543,2450000
51
+ 0.01747564318910225,202.05,1.1779218989389746,19.4162240816432,0.7587387420311582,-264.3634359927352,0.0033313218776882727,2.188614807909703,0.20012006799936302,0.4190979564586278,1.0,0.0,249324.70000000007,2.8351498844330543,2500000
52
+ 0.01739164350807681,930.28,148.72915517812908,105.18675646880733,18.012205716423182,-264.5713771661378,-0.010254100840389812,2.1405313886904955,0.19889803603574654,0.4159624411475638,1.0,0.0,249317.19999999995,2.8342251425891742,2550000
53
+ 0.016708987228498055,199.97,3.9381594685842773,19.374848617108178,1.1097791099381875,-264.37477506592194,-0.013524697916805585,2.098478674115565,0.19754113752693286,0.416748052054641,1.0,0.0,249321.60000000003,2.834693518438437,2600000
54
+ 0.01691228162311,1000.0,0.0,113.53176701533094,1.098405428560494,-264.5030223828137,0.013609797634035194,2.160090568395833,0.19850021346256214,0.4195537531906313,1.0,0.0,249323.59999999998,2.8333225431328137,2650000
55
+ 0.016626411607097918,1000.0,0.0,113.03489073377982,0.8508148446041641,-264.47001841461037,-0.00703634114958325,2.125073198753014,0.19675050455942908,0.4132827960199077,1.0,0.0,249323.6000000001,2.834265308163963,2700000
56
+ 0.016569862923547552,381.58,142.10588868868172,41.168190856331066,17.28946504710822,-263.9059333074911,-0.0030094805733114145,2.268293034629186,0.19973926430418681,0.4310985927687553,1.0,0.0,249333.04000000004,2.836139780036073,2750000
57
+ 0.015682509492840502,878.61,209.55738569661537,99.55451889837921,25.402889860541837,-264.10122034698327,0.003926819582209073,2.287471526022515,0.19805682594284385,0.4231925489652154,1.0,0.0,249325.78,2.8349585856498103,2800000
58
+ 0.0158161434181593,939.97,157.0784807031186,107.76886151297771,17.83972196626665,-263.45711384521513,-0.005934456333219807,2.2102400814103986,0.200073889548777,0.4331984383153902,1.0,0.0,249323.78,2.834257365665509,2850000
59
+ 0.015519282111730183,997.03,29.551126882066615,113.23947237134138,3.5734873450007294,-262.79159692962537,-0.01139589774265918,2.3387591293089898,0.20038672574416003,0.4392624051852568,1.0,0.0,249319.76000000007,2.835416936768672,2900000
60
+ 0.017323813038375324,1000.0,0.0,113.56831161045575,1.0948942303192524,-261.63439391356957,0.02997983818557023,2.8205156736254824,0.2092498380567125,0.4787132861629146,1.0,0.0,249315.76,2.835849091976326,2950000
61
+ 0.013586111685354231,996.73,32.53608919338646,113.3569069228874,3.875574749850669,-260.65564431487985,-0.07794007869735516,3.157730346568223,0.2139681191892911,0.5285516850399907,1.0,0.0,249319.96000000002,2.838189006580838,3000000
hopper_medium_expert_sparse/mobile_based/diffusion/seed_42&timestamp_26-0317-001620/record/consoleout_backup.txt ADDED
The diff for this file is too large to render. See raw diff
 
hopper_medium_expert_sparse/mobile_based/diffusion/seed_42&timestamp_26-0317-001620/record/dynamics_training_progress.csv ADDED
File without changes
hopper_medium_expert_sparse/mobile_based/diffusion/seed_42&timestamp_26-0317-001620/record/hyper_param.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"config": "config_gormpo/hopper_medium_expert_7_diffusion.yaml", "algo_name": "mobile_gormpo", "task": "hopper-medium-expert-v2", "seed": 42, "device": "cuda:0", "dataset_path": "/public/d4rl/sparse_datasets/hopper_medium_expert_sparse_78.pkl", "dynamics_path": "log/hopper-medium-expert-v2/seed_42&timestamp_26-0112-030627/model", "reward_penalty_coef": 0.5, "classifier_model_name": "/public/gormpo/models/hopper_medium_expert_sparse_3/diffusion/checkpoint.pt", "use_wandb": true, "wandb_project": "mobile-gormpo", "wandb_entity": null, "domain": "gym", "actor_lr": 0.0001, "critic_lr": 0.0003, "hidden_dims": [256, 256], "gamma": 0.99, "tau": 0.005, "alpha": 0.2, "auto_alpha": true, "target_entropy": -3.0, "alpha_lr": 0.0001, "deterministic_backup": true, "max_q_backup": false, "norm_reward": false, "num_q_ensemble": 2, "dynamics_lr": 0.001, "dynamics_max_epochs": null, "max_epochs_since_update": 5, "dynamics_hidden_dims": [200, 200, 200, 200], "dynamics_weight_decay": [2.5e-05, 5e-05, 7.5e-05, 7.5e-05, 0.0001], "n_ensemble": 7, "n_elites": 5, "rollout_freq": 1000, "rollout_batch_size": 50000, "rollout_length": 5, "penalty_coef": 1.5, "num_samples": 10, "model_retain_epochs": 5, "real_ratio": 0.05, "load_dynamics_path": null, "epoch": 3000, "step_per_epoch": 1000, "eval_episodes": 100, "batch_size": 256, "lr_scheduler": true, "density_model": "diffusion", "data_path": "/public/d4rl/sparse_datasets/hopper_medium_expert_sparse_78.pkl", "penalty_type": "tanh", "obs_shape": [11], "action_dim": 3.0, "max_action": 1.0, "classifier_type": "diffusion"}
hopper_medium_expert_sparse/mobile_based/diffusion/seed_456&timestamp_26-0318-182716/record/consoleout_backup.txt ADDED
The diff for this file is too large to render. See raw diff
 
hopper_medium_expert_sparse/mobile_based/diffusion/seed_456&timestamp_26-0318-182716/record/dynamics_training_progress.csv ADDED
File without changes
hopper_medium_expert_sparse/mobile_based/diffusion/seed_456&timestamp_26-0318-182716/record/hyper_param.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"config": "config_gormpo/hopper_medium_expert_7_diffusion.yaml", "algo_name": "mobile_gormpo", "task": "hopper-medium-expert-v2", "seed": 456, "device": "cuda:0", "dataset_path": "/public/d4rl/sparse_datasets/hopper_medium_expert_sparse_78.pkl", "dynamics_path": "log/hopper-medium-expert-v2/seed_456&timestamp_26-0112-030630/model", "reward_penalty_coef": 0.5, "classifier_model_name": "/public/gormpo/models/hopper_medium_expert_sparse_3/diffusion/checkpoint.pt", "use_wandb": true, "wandb_project": "mobile-gormpo", "wandb_entity": null, "domain": "gym", "actor_lr": 0.0001, "critic_lr": 0.0003, "hidden_dims": [256, 256], "gamma": 0.99, "tau": 0.005, "alpha": 0.2, "auto_alpha": true, "target_entropy": -3.0, "alpha_lr": 0.0001, "deterministic_backup": true, "max_q_backup": false, "norm_reward": false, "num_q_ensemble": 2, "dynamics_lr": 0.001, "dynamics_max_epochs": null, "max_epochs_since_update": 5, "dynamics_hidden_dims": [200, 200, 200, 200], "dynamics_weight_decay": [2.5e-05, 5e-05, 7.5e-05, 7.5e-05, 0.0001], "n_ensemble": 7, "n_elites": 5, "rollout_freq": 1000, "rollout_batch_size": 50000, "rollout_length": 5, "penalty_coef": 1.5, "num_samples": 10, "model_retain_epochs": 5, "real_ratio": 0.05, "load_dynamics_path": null, "epoch": 3000, "step_per_epoch": 1000, "eval_episodes": 100, "batch_size": 256, "lr_scheduler": true, "density_model": "diffusion", "data_path": "/public/d4rl/sparse_datasets/hopper_medium_expert_sparse_78.pkl", "penalty_type": "tanh", "obs_shape": [11], "action_dim": 3.0, "max_action": 1.0, "classifier_type": "diffusion"}
hopper_medium_expert_sparse/mobile_based/diffusion/seed_456&timestamp_26-0318-182716/record/policy_training_progress.csv ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ alpha,eval/episode_length,eval/episode_length_std,eval/normalized_episode_reward,eval/normalized_episode_reward_std,loss/actor,loss/alpha,loss/critic,penalty/lcb_mean,penalty/lcb_std,rollout_info/dynamics_penalty_mean,rollout_info/dynamics_penalty_std,rollout_info/num_transitions,rollout_info/reward_mean,timestep
2
+ 0.22516476637139887,34.21,1.8291801442176219,1.9744385804224787,0.7245634431850805,-260.41639529782236,-1.3119720290943182,9.435601860337824,0.3282620125856165,0.4626234982547097,1.0,0.0,249245.72,2.950117284377797,50000
3
+ 0.06509166212223423,27.0,14.1124058898545,1.7874690538562985,1.6183835600423908,-352.3137120062272,-0.038120855535379694,11.454790622095882,0.28114013921469927,0.5058487635079028,1.0,0.0,249333.04000000004,2.895132901716986,100000
4
+ 0.04914017807088825,60.55,0.7533259586659681,4.186199097614414,0.6748762698608203,-300.96453895507995,-0.033171834354139326,7.064138721293195,0.2094290601593263,0.34944603267997437,1.0,0.0,249327.75999999992,2.8854451388489766,150000
5
+ 0.0393888325452058,58.74,0.6102458520956943,3.9761623242968875,0.6653897192699574,-291.9509248846408,-0.009007259873747798,4.939586199094005,0.1874930071182579,0.3179487949383235,1.0,0.0,249332.06,2.8847288017005606,200000
6
+ 0.033810815094411396,199.34,1.744820907715173,19.31619440348222,0.7963427372160443,-283.3687843493667,-0.03841669326819472,4.954360751444095,0.17656077538966886,0.29571740860909057,1.0,0.0,249318.74000000008,2.8611575699051928,250000
7
+ 0.028925089695937867,105.38,0.8919641248391101,7.901636215333914,0.6881776745792619,-268.96274063751616,-0.012084339155033364,4.628922469475208,0.16632526895210314,0.2811434564739491,1.0,0.0,249324.48000000004,2.8520970685641354,300000
8
+ 0.027543633728548678,108.24,0.9604165762834375,8.18607830608754,0.7008326352199356,-263.8975737042245,0.04330282257620256,6.36870135504716,0.1686689834842074,0.2894483010569198,1.0,0.0,249318.25999999998,2.840413739999844,350000
9
+ 0.023548197555430184,120.81,0.9348261870529732,9.835041742087263,0.7080260621995134,-266.0303808895924,-0.04735454967424267,3.513122453782564,0.166476823723614,0.29743793384939643,1.0,0.0,249325.84000000003,2.8329628874171964,400000
10
+ 0.023651391242928987,979.79,89.38157472320566,109.14224075706316,10.66224933697603,-268.9692678427122,0.015680412805229398,4.2750465863793465,0.16516381177991518,0.3064410683929906,1.0,0.0,249307.0,2.84241105246664,450000
11
+ 0.02363302069302627,730.06,257.1142866508977,80.270928080015,30.072205947918775,-266.91004577666894,0.0052824028142914,4.024457637723111,0.168114692373126,0.31823959174320043,1.0,0.0,249310.28000000003,2.8407430686733344,500000
12
+ 0.02327392158288499,336.16,80.12549157415509,34.666280731536254,9.703152945700815,-266.6346187393227,-0.016646121448576127,3.505826199440977,0.17435943024665188,0.33318642238736274,1.0,0.0,249320.07999999993,2.8376825392176688,550000
13
+ 0.022777918879985596,857.06,228.56206246881834,96.00986903186362,26.1393358200531,-267.66138338928374,-0.00038234414808466244,4.230798703945201,0.17312133585706496,0.3338142534095093,1.0,0.0,249312.37999999995,2.8436367888506577,600000
14
+ 0.023929834091774984,552.3,201.98205365823966,63.28931078808936,23.391377006724788,-268.1242091116366,0.04953348229013329,5.701181092905935,0.17353756117865538,0.32661506147086217,1.0,0.0,249320.14,2.8457190831138774,650000
15
+ 0.022948825639150846,133.77,0.6611353870426239,10.532756141567571,0.6811856219409893,-268.72685243500223,0.0083688545276225,3.547237321885874,0.17767329496189976,0.34739274226367356,1.0,0.0,249313.58000000002,2.8430219767213165,700000
16
+ 0.023089362791553224,996.42,35.62055024841699,112.11868653210911,4.559981661734123,-268.4599752023314,0.005611374106257893,3.4956304950261137,0.17974597182005655,0.3450509914791555,1.0,0.0,249310.64,2.8488600104732558,750000
17
+ 0.0240343369841203,794.81,277.0950268409738,89.27956015523438,32.30226436251532,-268.1397083459478,-0.009585335047096117,3.917799200779249,0.17663173214644004,0.34048969299122966,1.0,0.0,249317.8200000001,2.8502385928773055,800000
18
+ 0.02374084282990552,1000.0,0.0,111.78856281123515,0.8481522926135725,-266.98998585296874,0.006062285657748976,5.172866314958925,0.18383823201045524,0.3545472150543289,1.0,0.0,249316.58000000002,2.837370356613105,850000
19
+ 0.02287816583696789,1000.0,0.0,110.83638274695635,1.0228311362117166,-266.99105861541364,0.00598643688842645,3.4082349436688473,0.1863026882795984,0.3668449999339886,1.0,0.0,249329.46000000002,2.835169755260675,900000
20
+ 0.02234944363109789,1000.0,0.0,112.48469796862149,0.8338292328277309,-268.380801575014,0.019128033715709696,3.6214188506710414,0.18210905273586364,0.3680253410388582,1.0,0.0,249327.12,2.8383708640822047,950000
21
+ 0.024393811788521545,1000.0,0.0,112.67703354794682,0.825131335420004,-267.7667863433879,0.003341597116552521,4.024155272096349,0.1855724929067497,0.37247455930843737,1.0,0.0,249326.64,2.8320801269297142,1000000
22
+ 0.023812154517248062,1000.0,0.0,112.78632238781925,0.7251792084932331,-266.58625160400385,-0.004610790544897275,3.265882465029947,0.18873754698484999,0.37766443876534744,1.0,0.0,249321.38000000003,2.8382085446428653,1050000
23
+ 0.024554094752967312,669.48,421.93045588106105,74.4611431850468,49.37184841755226,-265.15866972107193,0.0027728756761558186,4.307157886789401,0.18308016571029945,0.35976913873627264,1.0,0.0,249319.53999999992,2.84325633593742,1100000
24
+ 0.022230596364885575,1000.0,0.0,114.19896357260122,1.6372346561746038,-267.46148132477174,0.0021576345694813586,3.417384374660885,0.1755922021374112,0.34647188759088987,1.0,0.0,249318.95999999993,2.84583707590997,1150000
25
+ 0.02141412725642331,1000.0,0.0,113.15220382132725,0.7117275036011294,-268.37473952362086,-0.0029852199716122116,2.9635373138928847,0.1740630495305348,0.34263899966433825,1.0,0.0,249321.28,2.8408841965527603,1200000
26
+ 0.02169278495054705,1000.0,0.0,111.62619940519704,0.889009237806739,-268.5038973394799,-0.0033476760312914763,3.4906185518484927,0.17326231268316575,0.34297883315548205,1.0,0.0,249316.06000000003,2.841410379490258,1250000
27
+ 0.020964926201700824,1000.0,0.0,113.05245996655667,0.7016396529361506,-269.1657055419908,0.008598738474771292,2.697491738296163,0.1729592486433686,0.33735286241590834,1.0,0.0,249320.06,2.8392064806520754,1300000
28
+ 0.02133731116499773,1000.0,0.0,112.29672325102489,0.7946163392138442,-268.758358750614,0.004450755535140704,2.9532666064148967,0.1755905725502958,0.34887572366997555,1.0,0.0,249316.02000000002,2.838936994487137,1350000
29
+ 0.020489315667748483,1000.0,0.0,113.21547812878805,0.7655511550106179,-268.9492738546771,-0.0076163275832682896,2.6034325042039015,0.17369096509456536,0.34721631643518913,1.0,0.0,249316.46,2.840169521674466,1400000
30
+ 0.021480096188858454,1000.0,0.0,113.26320045571008,0.9257769305612507,-268.60308047394,0.012230453170687073,3.0724807562154828,0.17726191278159495,0.34956276572226913,1.0,0.0,249313.28000000003,2.8400818643324914,1450000
31
+ 0.020434438535906336,1000.0,0.0,113.07699383446202,0.7642738224898705,-268.44436485839645,-0.003808774939254076,2.5273084926963145,0.17784465238228322,0.3498119253578773,1.0,0.0,249313.91999999998,2.83695962165461,1500000
32
+ 0.022081366293318336,1000.0,0.0,113.0395520701903,0.730272240299038,-269.4096624844358,0.05608509906083321,4.5940811559653385,0.1750566745273755,0.3360991605313096,1.0,0.0,249315.26,2.841709745394726,1550000
33
+ 0.02187399929109956,136.53,0.9534673565466203,12.396585310038184,0.7064594201833284,-267.85019430420084,-0.006707017633281492,2.6209084054464244,0.1831296234402045,0.3579039038355665,1.0,0.0,249317.02,2.8397828172738913,1600000
34
+ 0.020176978778950645,1000.0,0.0,112.94549584109986,0.756895722406846,-267.69948319426976,0.009849740241766162,2.37873895982924,0.1817178922295585,0.3576233670204887,1.0,0.0,249314.16000000006,2.8378638746664047,1650000
35
+ 0.021240192049070798,784.58,373.11856507013965,87.8956124475524,44.16785361256252,-266.7877465530401,-0.001915130832977651,2.4973288991284472,0.18381809833154267,0.35876015541240686,1.0,0.0,249314.04000000004,2.838579540676843,1700000
36
+ 0.020013845343999713,124.84,0.6280127387243033,10.821824916409481,0.6688184760419709,-266.9218472067263,-0.007865608656033885,2.3274312207222327,0.1824548175217214,0.36009061327770575,1.0,0.0,249313.07999999987,2.8388301837700443,1750000
37
+ 0.019591331888176525,135.09,0.8842510955605313,12.20734827865628,0.709827980401028,-267.77265992309435,0.008366282330527742,2.3077372854733467,0.1831398046626152,0.3632157022202005,1.0,0.0,249329.7,2.8394454704210497,1800000
38
+ 0.020016331107430087,1000.0,0.0,112.69418506670073,0.7253345347625217,-267.87762681610235,0.0075482685861734825,2.7953296818667424,0.183082605666523,0.36192346463635877,1.0,0.0,249316.52000000008,2.8389622920648514,1850000
39
+ 0.019966500848941738,1000.0,0.0,112.77740764946654,0.7105217317873743,-268.4824465447968,0.01045217098630968,3.4009490062284398,0.17959755225911747,0.3547003421570322,1.0,0.0,249323.64,2.840190288652105,1900000
40
+ 0.01965930767357325,617.96,430.99953410647674,68.4265199276207,50.87883044098449,-268.15868716430685,-0.008700041885152606,2.224116650595098,0.18456276385694828,0.37035124824508453,1.0,0.0,249315.88000000003,2.8393256825225435,1950000
41
+ 0.019393677841685553,621.55,386.7717253109384,68.98918812002613,45.9433620252121,-267.4133657489041,0.0013329361412674416,2.7720948760814035,0.18654089848726826,0.37948111074790547,1.0,0.0,249304.87999999998,2.839469214925857,2000000
42
+ 0.018914294517747805,1000.0,0.0,113.13804309318397,0.7105545239790318,-267.5868982293709,0.020081937098577574,2.699999724180721,0.18536030145153337,0.3760228683851657,1.0,0.0,249316.43999999992,2.840274062080551,2050000
43
+ 0.018060083462185905,1000.0,0.0,113.39626712122333,0.7279103312476107,-267.53476506896783,-0.004689826344624311,2.366798812820282,0.18255294185072032,0.36853550291656495,1.0,0.0,249312.34000000003,2.8385398430626316,2100000
44
+ 0.018397723234854755,1000.0,0.0,113.64839151888162,0.7367984622320068,-267.9990053753636,-0.01432757407881283,2.3528297686338813,0.18598806735187823,0.37497720737278173,1.0,0.0,249314.82000000004,2.8367034576551537,2150000
45
+ 0.01891055768709635,1000.0,0.0,113.50366329701093,0.7629685416358691,-267.98882468779885,-0.006899681616947281,3.1668298501097825,0.18438097698419967,0.3735097944691738,1.0,0.0,249315.50000000012,2.8361365151057125,2200000
46
+ 0.017536492801048055,1000.0,0.0,112.95673240506893,0.7080680010389221,-268.26428903960414,0.002822860445976337,2.629040147054835,0.1837534650072451,0.3740363048253913,1.0,0.0,249316.44,2.836059717106276,2250000
47
+ 0.017718943607434583,1000.0,0.0,112.73267399233472,0.8149470738776338,-268.31595238311553,-0.0007334396434576615,2.7502933281850974,0.1841732982991624,0.3751109433871482,1.0,0.0,249315.47999999998,2.8366706189601936,2300000
48
+ 0.016778614944927387,1000.0,0.0,113.05967522134578,0.7136598998896244,-268.29410487213454,-0.02677965620495366,2.416846380258813,0.1842385225822039,0.3764589790426168,1.0,0.0,249310.24000000002,2.833950567533395,2350000
49
+ 0.01621860975911816,1000.0,0.0,113.13088540917487,0.9245144905710169,-268.2279561245797,0.01309280080601591,2.1272703775149684,0.18674716297358124,0.3841773280753215,1.0,0.0,249320.4399999999,2.834412188466215,2400000
50
+ 0.016273186139874152,1000.0,0.0,113.08280710740468,0.7102435742256272,-267.50675817290505,0.011096555777862505,2.377953774518959,0.1897347116433088,0.39277786907002343,1.0,0.0,249318.82000000004,2.8374204599057142,2450000
51
+ 0.01652659449588469,825.18,349.6402831482666,92.50825878737494,41.441353098525404,-266.8225286672976,-0.0008600063184647845,2.706197876782419,0.18920922579511992,0.3919166543573121,1.0,0.0,249314.45999999988,2.8365374253248072,2500000
52
+ 0.01659326956730335,1000.0,0.0,113.54601191939851,0.7175870558079078,-267.0488162942507,0.007637227197811099,2.4786103723829824,0.18848568529740034,0.39008451252102533,1.0,0.0,249315.21999999994,2.837630998175534,2550000
53
+ 0.015830213272515752,123.58,0.680881781221968,10.556267071297711,0.6755186096805391,-266.9155471093739,-0.026184765093401435,2.082824450239561,0.1901040248873844,0.39520908089071494,1.0,0.0,249316.81999999998,2.836107922759186,2600000
54
+ 0.01587851645661527,1000.0,0.0,113.27061278246472,0.7254702862666695,-266.68444346404283,0.009284918102026552,2.357617076927441,0.19234599065303637,0.4025955991575049,1.0,0.0,249321.22,2.8370870028593393,2650000
55
+ 0.016366153102331207,1000.0,0.0,113.08382178903902,0.7280487459095071,-266.19275393249404,-0.01607442461997256,2.869184707822211,0.19311396257787616,0.40270422013163976,1.0,0.0,249323.74,2.83980287333577,2700000
56
+ 0.014640383170414805,1000.0,0.0,113.33561714664988,0.7176954561873063,-266.4260320996107,0.005476941750124081,1.8781621430402817,0.1911913619223223,0.40146631031811175,1.0,0.0,249310.37999999998,2.8354932583441306,2750000
57
+ 0.015179395705405645,782.42,376.8597930265313,87.86917806437668,44.87091696504088,-266.24560615356353,-0.011602714526876712,2.0726991913301003,0.19432281996220296,0.405888523220873,1.0,0.0,249311.28,2.8365722979856867,2800000
58
+ 0.01485439891943702,1000.0,0.0,113.1139267085441,0.7229706888900862,-265.8557194973761,0.011638054015710941,2.3200313598674414,0.19436659960717245,0.40801028997391225,1.0,0.0,249306.62,2.8376809691158877,2850000
59
+ 0.014446814695503596,231.46,283.80396121266523,23.225448607595933,33.85744176091226,-265.504919192814,-0.020491633216588957,2.052736263567202,0.19508276763454016,0.4121109072977304,1.0,0.0,249318.87999999998,2.8377370450090607,2900000
60
+ 0.014693965255152533,1000.0,0.0,113.29342408052807,0.72761159267852,-265.9059356072999,0.010302110109105355,2.1326442997216994,0.1934140360829237,0.40625860077023385,1.0,0.0,249311.89999999997,2.837628023484616,2950000
61
+ 0.013904633253682243,991.31,86.46440828456528,112.32720774183842,10.77348771429935,-265.3608404321293,-0.009237771067991915,2.1096950150585525,0.19782332797631952,0.41164641892284054,1.0,0.0,249321.34000000003,2.838897690288374,3000000
hopper_medium_expert_sparse/mobile_based/kde/seed_123&timestamp_26-0505-201136/record/consoleout_backup.txt ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ num rollout transitions: 246321, reward mean: 3.2922
2
+ num rollout transitions: 249046, reward mean: 3.4104
3
+ num rollout transitions: 249385, reward mean: 3.4258
4
+ num rollout transitions: 249305, reward mean: 3.4649
5
+ num rollout transitions: 249334, reward mean: 3.4735
6
+ num rollout transitions: 249347, reward mean: 3.4937
7
+ num rollout transitions: 249254, reward mean: 3.4778
8
+ num rollout transitions: 249383, reward mean: 3.4763
9
+ num rollout transitions: 249332, reward mean: 3.4586
10
+ num rollout transitions: 249285, reward mean: 3.5015
11
+ num rollout transitions: 249332, reward mean: 3.4704
12
+ num rollout transitions: 249333, reward mean: 3.4828
13
+ num rollout transitions: 249391, reward mean: 3.4500
14
+ num rollout transitions: 249359, reward mean: 3.5146
15
+ num rollout transitions: 249390, reward mean: 3.5303
16
+ num rollout transitions: 249370, reward mean: 3.5017
17
+ num rollout transitions: 249378, reward mean: 3.5136
18
+ num rollout transitions: 249283, reward mean: 3.4779
19
+ num rollout transitions: 249381, reward mean: 3.5343
20
+ num rollout transitions: 249311, reward mean: 3.5321
21
+ num rollout transitions: 249318, reward mean: 3.5174
22
+ num rollout transitions: 249380, reward mean: 3.5197
23
+ num rollout transitions: 249383, reward mean: 3.4979
24
+ num rollout transitions: 249246, reward mean: 3.4760
25
+ num rollout transitions: 249381, reward mean: 3.5215
26
+ num rollout transitions: 249391, reward mean: 3.5078
27
+ num rollout transitions: 249364, reward mean: 3.5369
28
+ num rollout transitions: 249334, reward mean: 3.5104
29
+ num rollout transitions: 249370, reward mean: 3.5451
30
+ num rollout transitions: 249341, reward mean: 3.5344
31
+ num rollout transitions: 249301, reward mean: 3.5348
32
+ num rollout transitions: 249430, reward mean: 3.5254
33
+ num rollout transitions: 249338, reward mean: 3.5222
34
+ num rollout transitions: 249368, reward mean: 3.5070
35
+ num rollout transitions: 249294, reward mean: 3.5251
36
+ num rollout transitions: 249394, reward mean: 3.5305
37
+ num rollout transitions: 249437, reward mean: 3.5110
38
+ num rollout transitions: 249268, reward mean: 3.5206
39
+ num rollout transitions: 249342, reward mean: 3.4984
hopper_medium_expert_sparse/mobile_based/kde/seed_123&timestamp_26-0505-201136/record/dynamics_training_progress.csv ADDED
File without changes
hopper_medium_expert_sparse/mobile_based/kde/seed_123&timestamp_26-0505-201136/record/hyper_param.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"config": "config_gormpo/hopper_medium_expert_78.yaml", "algo_name": "mobile_gormpo", "task": "hopper-medium-expert-v2", "seed": 123, "device": "cuda:3", "dataset_path": "/public/d4rl/sparse_datasets/hopper_medium_expert_sparse_78.pkl", "dynamics_path": "log/hopper-medium-expert-v2/seed_123&timestamp_26-0112-030632/model", "reward_penalty_coef": 0.3, "classifier_model_name": "/public/gormpo/models/hopper_medium_expert_sparse_3/kde", "use_wandb": true, "wandb_project": "mobile-gormpo", "wandb_entity": null, "domain": "gym", "actor_lr": 0.0001, "critic_lr": 0.0003, "hidden_dims": [256, 256], "gamma": 0.99, "tau": 0.005, "alpha": 0.2, "auto_alpha": true, "target_entropy": -3.0, "alpha_lr": 0.0001, "deterministic_backup": true, "max_q_backup": false, "norm_reward": false, "num_q_ensemble": 2, "dynamics_lr": 0.001, "dynamics_max_epochs": null, "max_epochs_since_update": 5, "dynamics_hidden_dims": [200, 200, 200, 200], "dynamics_weight_decay": [2.5e-05, 5e-05, 7.5e-05, 7.5e-05, 0.0001], "n_ensemble": 7, "n_elites": 5, "rollout_freq": 1000, "rollout_batch_size": 50000, "rollout_length": 5, "penalty_coef": 1.5, "num_samples": 10, "model_retain_epochs": 5, "real_ratio": 0.05, "load_dynamics_path": null, "epoch": 3000, "step_per_epoch": 1000, "eval_episodes": 100, "batch_size": 256, "lr_scheduler": true, "penalty_type": "tanh", "density_model": "kde", "target_dim": 14, "obs_shape": [11], "action_dim": 3.0, "max_action": 1.0, "classifier_type": "kde"}
hopper_medium_expert_sparse/mobile_based/kde/seed_123&timestamp_26-0505-201136/record/policy_training_progress.csv ADDED
File without changes
hopper_medium_expert_sparse/mobile_based/kde/seed_42&timestamp_26-0505-202702/record/consoleout_backup.txt ADDED
The diff for this file is too large to render. See raw diff
 
hopper_medium_expert_sparse/mobile_based/kde/seed_42&timestamp_26-0505-202702/record/dynamics_training_progress.csv ADDED
File without changes
hopper_medium_expert_sparse/mobile_based/kde/seed_42&timestamp_26-0505-202702/record/hyper_param.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"config": "config_gormpo/hopper_medium_expert_78.yaml", "algo_name": "mobile_gormpo", "task": "hopper-medium-expert-v2", "seed": 42, "device": "cuda:2", "dataset_path": "/public/d4rl/sparse_datasets/hopper_medium_expert_sparse_78.pkl", "dynamics_path": "log/hopper-medium-expert-v2/seed_42&timestamp_26-0112-030627/model", "reward_penalty_coef": 0.3, "classifier_model_name": "/public/gormpo/models/hopper_medium_expert_sparse_3/kde", "use_wandb": true, "wandb_project": "mobile-gormpo", "wandb_entity": null, "domain": "gym", "actor_lr": 0.0001, "critic_lr": 0.0003, "hidden_dims": [256, 256], "gamma": 0.99, "tau": 0.005, "alpha": 0.2, "auto_alpha": true, "target_entropy": -3.0, "alpha_lr": 0.0001, "deterministic_backup": true, "max_q_backup": false, "norm_reward": false, "num_q_ensemble": 2, "dynamics_lr": 0.001, "dynamics_max_epochs": null, "max_epochs_since_update": 5, "dynamics_hidden_dims": [200, 200, 200, 200], "dynamics_weight_decay": [2.5e-05, 5e-05, 7.5e-05, 7.5e-05, 0.0001], "n_ensemble": 7, "n_elites": 5, "rollout_freq": 1000, "rollout_batch_size": 50000, "rollout_length": 5, "penalty_coef": 1.5, "num_samples": 10, "model_retain_epochs": 5, "real_ratio": 0.05, "load_dynamics_path": null, "epoch": 3000, "step_per_epoch": 1000, "eval_episodes": 100, "batch_size": 256, "lr_scheduler": true, "penalty_type": "tanh", "density_model": "kde", "target_dim": 14, "obs_shape": [11], "action_dim": 3.0, "max_action": 1.0, "classifier_type": "kde"}
hopper_medium_expert_sparse/mobile_based/kde/seed_42&timestamp_26-0505-202702/record/policy_training_progress.csv ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ alpha,eval/episode_length,eval/episode_length_std,eval/normalized_episode_reward,eval/normalized_episode_reward_std,loss/actor,loss/alpha,loss/critic,penalty/lcb_mean,penalty/lcb_std,rollout_info/dynamics_penalty_mean,rollout_info/dynamics_penalty_std,rollout_info/num_transitions,rollout_info/reward_mean,timestep
2
+ 0.23472550793186303,32.36,0.7282856582413249,2.237319242043943,0.656452575930236,-304.47073843361943,-1.1833499600471886,12.605111927908457,0.3755086280263558,0.5621184342692582,0.0,0.0,249281.7,3.4900583034022796,50000
3
+ 0.07937059987873007,14.0,0.0,1.0796521945581803,0.6258220976772739,-409.56730356140326,-0.023013364989869518,13.336951364154938,0.3402569895800905,0.64219693325818,0.0,0.0,249328.1,3.4329471897183574,100000
4
+ 0.05220276025608221,66.84,0.6740919818541087,4.7356922481617065,0.6706543491574745,-344.5820681262143,-0.051516410076506286,10.359994436583543,0.22353499569028576,0.4605541362255751,0.0,0.0,249320.72,3.3705175934329135,150000
5
+ 0.040341788921431206,73.03,0.8056674251823763,5.2348499394857555,0.6770129543256713,-326.63497375854877,-0.03275317510295626,7.087187332328594,0.18935782330587636,0.38899478830695405,0.0,0.0,249325.91999999993,3.3697335855913155,200000
6
+ 0.037300602987706565,332.34,73.34319600344669,35.24161072867958,8.98424556811818,-314.5687447564658,-0.0028683713971823627,6.191781066579858,0.18705882769331372,0.3503861022588583,0.0,0.0,249324.1,3.366469036044377,250000
7
+ 0.03465051179274942,340.98,42.752773009478574,36.174159333039555,6.325704751469502,-312.90093849853514,0.009335477132759784,6.949369702718223,0.17722320933520685,0.33543789218008374,0.0,0.0,249320.75999999998,3.3700957393158,300000
8
+ 0.03362932213600726,408.04,139.82052209886788,44.388462375719804,16.893939489885398,-309.8188840289316,0.02351379434060314,6.540811592171242,0.18100312249034234,0.34891839417934767,0.0,0.0,249319.88,3.365833043882194,350000
9
+ 0.032529771716743566,547.14,208.47158175636312,60.23355646628501,24.584495505628418,-310.9785167797848,-0.02698224392883473,4.23281141690252,0.1908507797290363,0.3634620570591134,0.0,0.0,249337.29999999996,3.3549204400789128,400000
10
+ 0.030669649376384788,393.31,66.13768895266904,42.95770295893973,8.431328901686923,-312.3856444134494,0.006193701621293912,5.275232379081227,0.1828503515972188,0.3730780624400081,0.0,0.0,249328.87999999995,3.345472311463679,450000
11
+ 0.030422223398573874,456.43,207.6853511926154,50.13926219319879,24.39575907108245,-313.06324876709175,-0.0018314874582737348,4.737899662048813,0.18579959889769507,0.377505364297624,0.0,0.0,249322.40000000005,3.351296016912657,500000
12
+ 0.030961527554094752,208.95,0.9836157786453001,20.56122671786683,0.7030726645509581,-313.4172430426042,0.0010777576421575257,5.912826517461028,0.1862312954989091,0.3798326677823039,0.0,0.0,249326.04000000004,3.34667190060694,550000
13
+ 0.030154000728801013,46.31,0.783517708797957,2.870336479810043,0.6692287019932478,-312.5331250646951,0.023231456039622008,5.2268767143286325,0.19176937890499865,0.38763333613767925,0.0,0.0,249326.18,3.341766058957413,600000
14
+ 0.030886988302692965,183.37,37.403383536787146,17.092173418696447,5.225484173597068,-308.55422147399526,0.002320033294521464,5.424860504794046,0.20379115223497157,0.4119960378667742,0.0,0.0,249326.43999999994,3.3391040820083973,650000
15
+ 0.030396659606210758,51.05,0.47696960070847283,3.2293522621376956,0.6499178323683812,-308.91362767089936,-0.010658302422985396,5.6716633293449945,0.20156384399056487,0.41797783879340117,0.0,0.0,249327.80000000002,3.3367726796221935,700000
16
+ 0.031406667321063474,524.65,287.54854807492944,56.14561559761788,33.082380511349726,-310.7588708758476,0.028405747065320567,7.440956529987926,0.20071256706356919,0.4061892252801335,0.0,0.0,249328.72,3.3400961960953386,750000
17
+ 0.02852692071877418,27.29,0.6970652767137379,1.7282750476954698,0.6588522819434786,-309.96888952515263,0.002674000100866031,4.79051947882413,0.2005510697650926,0.41298937327057195,0.0,0.0,249329.91999999995,3.331206293127866,800000
18
+ 0.027895236294567416,125.5,2.1095023109728985,10.20705296316274,0.8432486397057699,-310.6252380633516,-0.008303249069154204,4.073310986422307,0.20259128175556423,0.41605742157667697,0.0,0.0,249331.44000000006,3.3384178843778045,850000
19
+ 0.027071060805767905,38.63,0.743706931526122,2.557664097005566,0.6639683034129807,-310.7310512908887,-0.002688230028077824,4.234364567153457,0.20138795411855198,0.41135884366109693,0.0,0.0,249347.61999999997,3.342214167949324,900000
20
+ 0.02721804361008086,39.92,0.68818602136341,2.6232949991027636,0.6619976017126776,-311.3363322698996,0.013127833685651643,4.704828136595517,0.2048616201707745,0.41927648533612105,0.0,0.0,249333.05999999994,3.346586593649594,950000
21
+ 0.02701455308448546,975.28,80.78490948190756,110.79982186670718,9.49157063541856,-311.29956006164804,-0.012583795052543381,4.495903097749957,0.20402387019634027,0.4209232899072757,0.0,0.0,249324.82,3.345228926947039,1000000
22
+ 0.026472097738906682,31.67,0.9492628719169417,1.9549960410447258,0.6771657338275361,-311.2388062023876,0.004154857403673288,4.182996469436846,0.20123854168444855,0.4246227018374205,0.0,0.0,249329.34,3.342169500023907,1050000
23
+ 0.026009654140137287,42.39,0.7601973427998812,2.6385020955089864,0.6810147577472231,-311.5623889550746,-0.0005213278279453953,4.351508018431701,0.20087412087947124,0.42588429044008164,0.0,0.0,249336.32000000004,3.3443495413822673,1100000
24
+ 0.026425738099105634,867.07,243.2671475970399,97.09959753751514,29.067957090001865,-311.05775023498535,0.014633689657077446,4.954487686979755,0.20644904245287293,0.43551299742281235,0.0,0.0,249327.45999999993,3.3442489295001456,1150000
25
+ 0.02645752524502536,1000.0,0.0,112.82734798005716,0.8187272951802478,-311.40712682983406,-0.011977577918805086,4.733954174633017,0.19973177153140434,0.4233388217528154,0.0,0.0,249325.14,3.3453140158542993,1200000
26
+ 0.025682599809393455,146.69,0.8682741502544,12.819073158633435,0.7363813835317679,-310.9971414501948,0.00398410417482254,4.0949563669621565,0.200877039806543,0.4260943652819097,0.0,0.0,249320.88,3.3459583752174273,1250000
27
+ 0.02515949494250151,49.53,0.49909918853871127,3.1156576486362177,0.6600693298273566,-311.78712645080515,0.004138654838278758,3.954071571788167,0.19976124206081125,0.4229986124497685,0.0,0.0,249324.98,3.348064753963924,1300000
28
+ 0.02590705194007613,1000.0,0.0,113.00142295170821,0.7642185105340347,-311.02684086608946,0.010931610305085562,4.147341764501201,0.20392112524211478,0.43670757683127764,0.0,0.0,249332.0,3.3487876416334004,1350000
29
+ 0.025945866969823882,852.39,228.27316508954792,96.18101999917627,27.553026383098945,-310.6600995648162,-0.0017740021697431234,4.165624664763288,0.20278758342892036,0.43480570635646315,0.0,0.0,249328.16000000003,3.3450475471477987,1400000
30
+ 0.026072245154641384,1000.0,0.0,113.03523001097247,0.921881855226048,-310.7070849273618,-0.003408802383542238,5.041586709044002,0.2039517697709773,0.44247738862335634,0.0,0.0,249332.5,3.3475514738501992,1450000
31
+ 0.02492650051154171,139.34,0.8627861844049196,11.930851984029994,0.7059224695666511,-310.5350261987278,0.006621640182733526,3.577211349526668,0.204666828055086,0.4457018877860921,0.0,0.0,249320.81999999992,3.346064202533999,1500000
32
+ 0.024778469551839016,665.2,200.48476251326434,75.88216154722609,23.087285002425702,-311.19302110840147,0.013347693330049135,4.72832798374058,0.20538207540303227,0.4420830759420951,0.0,0.0,249318.23999999996,3.3452854413972637,1550000
33
+ 0.02449796011179699,909.08,180.44282640215985,102.43568699113122,21.67647731206506,-310.5995187701436,-0.02004648855827735,3.4006915364611427,0.2043336878465141,0.44732843300163594,0.0,0.0,249321.75999999998,3.3456219480636418,1600000
34
+ 0.024362850225157863,911.76,143.21306644297508,102.30812652945669,17.37431615477256,-311.2707502972385,0.005598737913221167,3.821451601095823,0.20448525478392798,0.44495916865080726,0.0,0.0,249328.12000000008,3.3408772577464516,1650000
35
+ 0.025173943881578502,1000.0,0.0,112.5226160678842,0.801488561334761,-310.9078240527375,0.008037987480238115,3.6901108077108558,0.21196277905225916,0.4671819453296117,0.0,0.0,249320.66,3.3407050682971056,1700000
36
+ 0.0245801404714581,1000.0,0.0,112.63439486587494,0.7219227332812224,-311.4410817608611,-0.007518770416080423,3.345180911601806,0.20850445707962073,0.46436290615797104,0.0,0.0,249327.92000000004,3.339648054121625,1750000
37
+ 0.02645972441833484,985.62,67.17511146250523,111.25079358496737,8.374154550042427,-311.568600294798,0.03460130716700078,6.563829163455893,0.20789221378162817,0.4474363232395046,0.0,0.0,249322.40000000002,3.3432682271475502,1800000
38
+ 0.024756703382357782,1000.0,0.0,112.62551336553057,0.7292093017372011,-310.3795550000045,-0.02021857757873846,3.24260490222574,0.2103924268321674,0.46927527602016583,0.0,0.0,249333.7,3.340915887809879,1850000
39
+ 0.023669329418652036,849.25,212.18988547996344,94.68421332399728,25.484914734786212,-311.1804454150404,0.007042281110957384,3.5142156049787716,0.20854573993101394,0.4725705182445044,0.0,0.0,249328.54,3.338367150744137,1900000
40
+ 0.02330327674195176,995.79,41.88897110218869,112.39597754166499,5.490036920221223,-311.37190493103054,-0.005704662882536471,3.7087253497183053,0.20972507816627609,0.4693083991476926,0.0,0.0,249318.69999999995,3.3423643010859054,1950000
41
+ 0.023582188880742067,1000.0,0.0,112.82039782727311,0.7076255762673357,-311.64521407347985,0.0012120505803822716,3.835411066834889,0.20930990316912457,0.469495400493144,0.0,0.0,249332.02000000002,3.342346324477573,2000000
42
+ 0.022686616912856877,1000.0,0.0,113.05450828361433,0.7979734926817941,-311.97437498779186,-0.004320099861323929,3.493072681283953,0.20744186884835436,0.46368013651937834,0.0,0.0,249331.78,3.339863384577198,2050000
43
+ 0.022958624760062062,1000.0,0.0,113.20252038159255,0.8688420907013676,-311.8968978906279,0.004999502855688261,3.2551012090563383,0.20875842455267696,0.4687768258681901,0.0,0.0,249329.72,3.339095884693688,2100000
44
+ 0.023436123750358785,1000.0,0.0,112.84804387874242,0.714982051282628,-311.71530375793657,-0.0030845689506081553,3.565745526565925,0.20937369667112865,0.46561036621570756,0.0,0.0,249329.8200000001,3.3427451182090318,2150000
45
+ 0.02342705313827812,119.85,0.9937303457175896,9.96631739857251,0.7137272695264891,-311.52650401183996,-0.0028028284300119343,3.3372505813372166,0.20972105930417761,0.468607315844591,0.0,0.0,249326.28,3.339549047099701,2200000
46
+ 0.023455383235849718,1000.0,0.0,112.823228682987,0.7029846994868142,-311.38016343688787,0.003746444461531823,3.422588945817971,0.2115216228459781,0.4714778253450995,0.0,0.0,249327.15999999995,3.338744790862399,2250000
47
+ 0.023100156264416884,1000.0,0.0,113.41369145082282,0.7199877863435056,-311.4570016479432,0.004503001620024511,3.2970931001066734,0.21151650234565172,0.47309199672013613,0.0,0.0,249338.52000000002,3.3358441437338433,2300000
48
+ 0.022697284897789365,1000.0,0.0,112.61546007087769,0.7378342473671007,-311.54779344909656,-0.007868080153539677,3.416160187573415,0.21268673817977177,0.47512704673528655,0.0,0.0,249312.74,3.337204560690641,2350000
49
+ 0.022579501254521583,1000.0,0.0,113.06495641388945,0.7006661274836342,-311.1860677337645,-0.003601391148492634,3.53233315282349,0.2160681038998064,0.48861283017903645,0.0,0.0,249319.82000000007,3.336366084386437,2400000
50
+ 0.0229905577619742,1000.0,0.0,113.12555745215703,0.7069139365672207,-310.8591088684072,0.004478022935613877,3.3236129706668573,0.214911598485114,0.48261149354726285,0.0,0.0,249333.06,3.333677008878976,2450000
51
+ 0.023402626241408257,1000.0,0.0,113.19894582461296,0.7326673930527408,-310.89539396362306,-0.003053926188200686,3.3480884600115095,0.2169451598611466,0.4890530719807784,0.0,0.0,249324.34,3.333684868654672,2500000
52
+ 0.023059460310377262,1000.0,0.0,113.1144798120783,0.7288754323608579,-311.04225247680444,0.008203876112475656,4.1824724633591694,0.21451175718247964,0.4794298370945458,0.0,0.0,249331.4,3.335866781505846,2550000
53
+ 0.022477824609689168,1000.0,0.0,112.94163172372424,0.7227862117834448,-310.4666196618668,-0.012318696665391177,3.272924112651336,0.21729816889077577,0.4881206727761041,0.0,0.0,249323.00000000003,3.335461344950702,2600000
54
+ 0.02242735668640562,1000.0,0.0,112.92946884279793,0.7117998868022202,-310.53715101867346,0.0018883916274458326,3.380295277589605,0.2163913640187692,0.4863408929052941,0.0,0.0,249325.75999999998,3.3333323626572655,2650000
55
+ 0.02215920730493977,1000.0,0.0,112.9603529660608,0.7282883186311468,-310.1155329626467,0.0034662406364083056,3.206116565669775,0.21928658195867778,0.4989799505299306,0.0,0.0,249331.46000000002,3.3349885403331165,2700000
56
+ 0.021960359975807343,1000.0,0.0,112.85061305361145,0.7300181714105852,-310.1529010681165,0.0005277738993614408,3.317136748783592,0.21843467721670784,0.4966758086061517,0.0,0.0,249306.33999999994,3.3346067186114348,2750000
57
+ 0.021638918763100704,1000.0,0.0,112.99244757886417,0.7296398406936662,-310.47978156127544,-0.013830002743303895,3.2080009954374864,0.21770048576623338,0.4979199880066429,0.0,0.0,249314.96,3.3330782743265503,2800000
58
+ 0.02086537243306636,1000.0,0.0,112.855432129198,0.7345529517145756,-310.44069283568933,-0.00178063516605631,3.387521875775456,0.21896891655043,0.49942675591945446,0.0,0.0,249312.91999999995,3.3357009707201053,2850000
59
+ 0.021380764675662016,1000.0,0.0,112.94448125909841,0.7264935960043831,-309.6492685595716,0.003245809210688028,3.208275567445168,0.22424253181457401,0.5137360537278675,0.0,0.0,249313.23999999993,3.334653813641837,2900000
60
+ 0.020866245681979007,1000.0,0.0,112.8724350867999,0.7215828528234046,-309.20709205688405,-0.007367011932656064,3.2010774969732347,0.22556779478579733,0.5183634685769559,0.0,0.0,249333.0000000001,3.3353096598182046,2950000
61
+ 0.021997357800900896,1000.0,0.0,112.94400615297646,0.7278278777787316,-308.97226561340784,0.0404937107268717,3.0670675141954553,0.22660864659637153,0.5221275438842241,0.0,0.0,249321.92,3.3331490050073365,3000000
hopper_medium_expert_sparse/mobile_based/kde/seed_456&timestamp_26-0505-202659/record/consoleout_backup.txt ADDED
The diff for this file is too large to render. See raw diff
 
hopper_medium_expert_sparse/mobile_based/kde/seed_456&timestamp_26-0505-202659/record/dynamics_training_progress.csv ADDED
File without changes
hopper_medium_expert_sparse/mobile_based/kde/seed_456&timestamp_26-0505-202659/record/hyper_param.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"config": "config_gormpo/hopper_medium_expert_78.yaml", "algo_name": "mobile_gormpo", "task": "hopper-medium-expert-v2", "seed": 456, "device": "cuda:4", "dataset_path": "/public/d4rl/sparse_datasets/hopper_medium_expert_sparse_78.pkl", "dynamics_path": "log/hopper-medium-expert-v2/seed_456&timestamp_26-0112-030630/model", "reward_penalty_coef": 0.3, "classifier_model_name": "/public/gormpo/models/hopper_medium_expert_sparse_3/kde", "use_wandb": true, "wandb_project": "mobile-gormpo", "wandb_entity": null, "domain": "gym", "actor_lr": 0.0001, "critic_lr": 0.0003, "hidden_dims": [256, 256], "gamma": 0.99, "tau": 0.005, "alpha": 0.2, "auto_alpha": true, "target_entropy": -3.0, "alpha_lr": 0.0001, "deterministic_backup": true, "max_q_backup": false, "norm_reward": false, "num_q_ensemble": 2, "dynamics_lr": 0.001, "dynamics_max_epochs": null, "max_epochs_since_update": 5, "dynamics_hidden_dims": [200, 200, 200, 200], "dynamics_weight_decay": [2.5e-05, 5e-05, 7.5e-05, 7.5e-05, 0.0001], "n_ensemble": 7, "n_elites": 5, "rollout_freq": 1000, "rollout_batch_size": 50000, "rollout_length": 5, "penalty_coef": 1.5, "num_samples": 10, "model_retain_epochs": 5, "real_ratio": 0.05, "load_dynamics_path": null, "epoch": 3000, "step_per_epoch": 1000, "eval_episodes": 100, "batch_size": 256, "lr_scheduler": true, "penalty_type": "tanh", "density_model": "kde", "target_dim": 14, "obs_shape": [11], "action_dim": 3.0, "max_action": 1.0, "classifier_type": "kde"}
hopper_medium_expert_sparse/mobile_based/kde/seed_456&timestamp_26-0505-202659/record/policy_training_progress.csv ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ alpha,eval/episode_length,eval/episode_length_std,eval/normalized_episode_reward,eval/normalized_episode_reward_std,loss/actor,loss/alpha,loss/critic,penalty/lcb_mean,penalty/lcb_std,rollout_info/dynamics_penalty_mean,rollout_info/dynamics_penalty_std,rollout_info/num_transitions,rollout_info/reward_mean,timestep
2
+ 0.23616196421876964,65.53,0.5376802023508026,4.113844250276519,0.6892372163447942,-309.35745856993526,-1.1044867362214021,11.463249853691732,0.3914050846726899,0.5514006727172106,0.0,0.0,249244.14000000004,3.472270300683957,50000
3
+ 0.06610422911025662,68.37,0.6731270311018568,4.801851642774295,0.6682369710391176,-393.7263086010728,-0.030758322170376787,12.170041943626455,0.2989230725708632,0.5717776692423188,0.0,0.0,249326.0,3.434275587949831,100000
4
+ 0.05543095540761922,68.95,0.683739716558867,4.711146194245621,0.6673762558778528,-355.44893576782266,-0.011686449686363077,9.709768947067298,0.2490396477416132,0.44647031281143623,0.0,0.0,249319.11999999994,3.3866940472042275,150000
5
+ 0.04739700562462243,154.92,0.8084553172563095,12.755322280450715,0.7088461695050008,-318.31877720275526,-0.01738667241647759,8.905790511373374,0.20656537580698775,0.35197672830342924,0.0,0.0,249322.03999999998,3.3610073711797694,200000
6
+ 0.04141611922860216,225.51,2.229327252782776,21.426921831658934,0.9158591190106242,-297.01651430968576,-0.0273972767368335,6.669881233127053,0.20362350670039261,0.357048326750399,0.0,0.0,249329.83999999994,3.3468395712055883,250000
7
+ 0.03817897173114205,470.13,251.90262622688158,49.63607559513429,29.67464101207228,-295.5197691485579,-0.018162949502169963,6.591020081185097,0.20474532784938873,0.36703709249316957,0.0,0.0,249323.70000000004,3.344800942616931,300000
8
+ 0.033732697351798444,264.22,47.74464996206382,25.991971459042478,5.933865666088881,-298.3130650280808,-0.0008551837754249839,5.3620302669191835,0.2048234001714019,0.39586425766199673,0.0,0.0,249329.46,3.349074471338231,350000
9
+ 0.03298990890484358,42.3,0.47958315233127197,2.735636518634709,0.6517835594265492,-301.09524060729893,-0.010336240116208676,5.485735522379937,0.2047587168940885,0.4139720985889495,0.0,0.0,249326.86,3.3504533220218247,400000
10
+ 0.03103375739090175,966.54,145.84885464068617,105.19678916122852,17.02372631958366,-303.51531695800384,0.016807005483284686,5.625336678645674,0.20185486003056166,0.41312532099276683,0.0,0.0,249324.58,3.351905318523874,450000
11
+ 0.029520664987526566,356.71,75.62953060808985,36.85067352517339,9.22912583136797,-303.96229170959265,-0.011674643227905167,4.795224619362354,0.20741373047456185,0.42705876090466754,0.0,0.0,249318.59999999998,3.3452905007324576,500000
12
+ 0.03024360230296868,475.92,301.74488164673147,52.34350233241446,35.832397746919376,-302.3639689129631,0.02130455525957043,6.340410870137085,0.21909659784644886,0.44616579271018025,0.0,0.0,249313.44,3.3469086210735566,550000
13
+ 0.031056516798883514,135.99,1.3674428690076965,11.118564604737582,0.7444550397187807,-302.2623578985633,0.004073568980879855,6.251837473387709,0.22161974409818871,0.4568101342773428,0.0,0.0,249330.41999999998,3.3533555454696153,600000
14
+ 0.030179161320068287,1000.0,0.0,111.68569866043715,0.811741380835372,-301.6091094659425,0.004758735276535198,6.041676571922313,0.22425835517823833,0.46850884990274666,0.0,0.0,249315.90000000008,3.346836358457508,650000
15
+ 0.03102599773958332,170.29,34.470942835959676,15.214992236653426,4.801234912536283,-302.5870824517799,-0.0073156307002156555,5.845777298171618,0.22133787256747406,0.46124363055228745,0.0,0.0,249323.26000000007,3.3495504814120505,700000
16
+ 0.030984608155079474,129.61,0.9153687781435415,10.48450538367774,0.6948062169192747,-301.91743204895346,0.004662773890271915,5.028375654119271,0.21975058342456924,0.45869144626051217,0.0,0.0,249316.04,3.3420666540166413,750000
17
+ 0.03157522479470824,199.94,0.8924124606929245,18.950992077000432,0.7291645224384329,-301.27215558044304,0.005587125619910348,5.763680857641643,0.2306445412147056,0.4750768094468098,0.0,0.0,249311.34000000003,3.337870584516813,800000
18
+ 0.031248771163932997,1000.0,0.0,112.34964850409214,0.7088366447408472,-300.37883023804045,-0.0022596415929124537,5.179625581247907,0.2314580573612456,0.47587653852075706,0.0,0.0,249324.74000000002,3.3408318060972504,850000
19
+ 0.03244087874092221,277.16,11.429540673185427,27.781340824061,1.93242133687845,-301.10681750854405,0.012196369679793569,6.397392762279502,0.22930428983777984,0.47757645827948664,0.0,0.0,249320.18,3.3407813138779674,900000
20
+ 0.028855948416031937,120.46,0.7539230729988307,9.72146810638323,0.6794836208049556,-302.42964504455625,-0.013710838756263612,3.747829870427832,0.2197921763613804,0.45717581881284747,0.0,0.0,249318.28,3.341188438456047,950000
21
+ 0.028387335838377364,560.41,431.8187373192599,61.03849762496485,51.11431411093277,-304.3460370373579,-0.002079085017889876,5.103229226703683,0.22138071737677006,0.4749750647559737,0.0,0.0,249319.24000000005,3.3419159841561186,1000000
22
+ 0.028202604678385118,119.8,0.8831760866327847,9.712355764216857,0.6913313870770945,-305.4821149023448,0.00953390109024955,5.501450911694769,0.2169343176174155,0.46212441591501424,0.0,0.0,249298.68000000002,3.3441104092210954,1050000
23
+ 0.026764392469860742,111.89,0.8472897969408106,8.917087426693111,0.6895750752146448,-306.1333297131337,0.01277075443364702,3.5562800222051254,0.20986592598616888,0.4475688290899991,0.0,0.0,249313.34000000003,3.337217997783362,1100000
24
+ 0.02721339465424407,130.78,0.7011419257183242,10.594018289383177,0.6722153459646363,-308.11010023864907,-0.008793674870170718,3.5436016960430314,0.20587577248469027,0.44110381452158093,0.0,0.0,249314.40000000005,3.331594186494803,1150000
25
+ 0.027766433958262244,121.6,0.6,9.646489450069362,0.6663955791790895,-308.4440588592551,0.013415443982556317,5.327844600127887,0.2070948330989476,0.4380322524970789,0.0,0.0,249304.52000000005,3.33634319753987,1200000
26
+ 0.026212252728156773,1000.0,0.0,112.66658338296116,0.7356129787924308,-308.34456336975614,-0.003858099482953409,3.421322428303924,0.20991134599745248,0.451786383981409,0.0,0.0,249314.66000000006,3.3339736231665307,1250000
27
+ 0.025486357107758897,958.9,176.87365547192152,107.78425710224178,21.39452516874418,-308.8575260211162,0.007480437985286162,3.70518295326359,0.21182316532403248,0.45911011350542635,0.0,0.0,249322.48000000004,3.3375129168700224,1300000
28
+ 0.02514901217620837,1000.0,0.0,112.37444079400748,0.7388721481426869,-307.59414281311126,-0.009384782535433754,3.808798437757492,0.2147913166511052,0.4659936494487526,0.0,0.0,249320.26,3.338784520336265,1350000
29
+ 0.025256407730877086,938.51,175.67745985185462,105.49011201405527,21.084465138213737,-307.48962005553597,0.0008622622446716061,4.031336157139546,0.21592404900938117,0.4710600772589407,0.0,0.0,249311.56000000003,3.337472541598765,1400000
30
+ 0.0258026581263911,824.06,205.72966825424083,92.55070874919268,24.84976702361491,-307.3472048846386,0.004771668479666105,3.9946628300344624,0.21740666500836486,0.4743171441611657,0.0,0.0,249328.47999999992,3.338839418979466,1450000
31
+ 0.026107333574332568,991.94,80.19598743079358,110.41896189890991,9.900589896259406,-307.0844162304721,-0.006609873367771398,4.172080470317496,0.2237940710747226,0.49117863831162567,0.0,0.0,249317.64,3.339209330091354,1500000
32
+ 0.026479273398630442,993.0,69.6491205974634,109.0681891455253,8.627608834064523,-305.92764590697936,0.016451890041753472,4.701836036877658,0.2276731807789217,0.4980558096089982,0.0,0.0,249315.38000000003,3.341701732295358,1550000
33
+ 0.025944557772204287,1000.0,0.0,111.50147101619756,0.7120904079607231,-305.89168167114104,-0.0009427083125710046,3.783335398965466,0.22627365055411722,0.4946301887628419,0.0,0.0,249317.11999999997,3.335347901818983,1600000
34
+ 0.025822044002153228,1000.0,0.0,112.48975220248725,0.7253608945867147,-305.72522192993017,-0.008474405244588791,4.295624685333902,0.22715169335573793,0.49260672764867136,0.0,0.0,249326.07999999993,3.3398196682434254,1650000
35
+ 0.025383101748749876,1000.0,0.0,112.71509780234885,0.7263068710280345,-305.54700856628295,0.0007842290484905928,3.911757003061784,0.23137595057785734,0.5075867788258196,0.0,0.0,249316.65999999997,3.337303179896961,1700000
36
+ 0.024810148669182974,301.47,169.09911028742877,30.99510565534564,20.35480838615321,-305.70289047363497,-0.005587344206571418,4.023695352436314,0.23139808390647076,0.5134929717198012,0.0,0.0,249323.95999999993,3.3363551261280913,1750000
37
+ 0.024309326525069657,663.84,335.42619814200566,72.55383246000534,39.208828665368046,-305.4458357604971,0.005588231361806492,4.137559156603825,0.23080720044016861,0.5123609831649002,0.0,0.0,249320.84000000014,3.332395142901858,1800000
38
+ 0.024299052685834755,1000.0,0.0,111.82747955817516,0.7424056368389456,-304.8760386090102,0.010569464439079242,4.585861818784436,0.23268320238470905,0.5195610869279395,0.0,0.0,249335.06,3.333990721314743,1850000
39
+ 0.024173261111379164,1000.0,0.0,112.0837970782142,0.748159202167543,-304.81560472900367,-0.015591530402079098,4.3367479616593885,0.2299545067736501,0.5125764771795263,0.0,0.0,249328.06,3.332560518587902,1900000
40
+ 0.02351123286288211,1000.0,0.0,111.44180383846293,0.7722177053101573,-304.88102850158555,0.0014766968990117969,3.9975636749851318,0.2302094625243532,0.5142752273371888,0.0,0.0,249330.51999999993,3.3325481755891224,1950000
41
+ 0.02346388890322321,1000.0,0.0,112.44921091146448,0.733828363374985,-305.1052729132042,0.001235218036323976,3.893068474226039,0.22821035935193432,0.5119370310866848,0.0,0.0,249322.32,3.331956136677576,2000000
42
+ 0.022799979159906836,1000.0,0.0,111.83185894350896,0.7317954899209136,-305.95640877990553,-0.007437631253599952,3.883298093484645,0.22575510763943094,0.5019524359876028,0.0,0.0,249333.72,3.3311315364019136,2050000
43
+ 0.022780588950291236,21.65,0.7664854858377946,1.4394740510241844,0.6641457977381185,-305.8445238458232,-0.0036430536530167677,3.859482569353587,0.22466781306356037,0.49827247780709727,0.0,0.0,249317.47999999995,3.331657937310946,2100000
44
+ 0.02277560553163309,1000.0,0.0,112.39004206031811,0.7648231045411468,-305.6411173181117,-0.008148531781360678,4.179180003868321,0.22377710163041625,0.49623172294080453,0.0,0.0,249337.94000000003,3.3330796911984977,2150000
45
+ 0.021830717363841838,1000.0,0.0,112.07797365472967,0.723003757001316,-306.0277840918031,0.01542710261259207,3.8945836400174687,0.22400150964498447,0.501631925865103,0.0,0.0,249321.74,3.328672540282812,2200000
46
+ 0.022219976246692415,1000.0,0.0,112.43026303098847,0.7278776080835532,-305.4912009881605,-0.016673952379971768,3.589681844234429,0.22722383683413203,0.5050519949710357,0.0,0.0,249322.42,3.3326401323167296,2250000
47
+ 0.02154001674257245,853.25,349.3349216725977,96.0515878274188,40.36098871472045,-306.2225674346899,0.01467960385940938,3.359427652521167,0.22308251646578392,0.5010440938305889,0.0,0.0,249316.92,3.3305823838439137,2300000
48
+ 0.021360448953322963,1000.0,0.0,112.59049564526768,0.7350886415182523,-307.1200422393766,-0.0048482984960822465,2.990919958705308,0.22178270172253003,0.4915707315954559,0.0,0.0,249321.90000000005,3.331438595777642,2350000
49
+ 0.021495858762710495,1000.0,0.0,112.16498220202422,0.7414340281603611,-306.8127995080542,-0.008744818537905808,3.429394133219757,0.2223621268558506,0.4978687472876923,0.0,0.0,249323.74,3.329270788094183,2400000
50
+ 0.021169933738447767,1000.0,0.0,112.32185729455199,0.7281263356356681,-307.3031603430155,0.0007836605504900564,3.2493387729072643,0.21883757675632973,0.4905268417918697,0.0,0.0,249323.62000000005,3.3313544808954982,2450000
51
+ 0.021287632790468546,731.24,430.9753617087641,81.98403463154179,50.21165856696024,-307.30230646179746,-0.011503513159677337,3.0805082919680773,0.2199726228858542,0.4911502214944393,0.0,0.0,249317.6,3.332100061105371,2500000
52
+ 0.020996185100152838,1000.0,0.0,112.51216003733194,0.736104734869409,-307.17026753296307,0.0037213071484120857,3.1459426894622977,0.22127503864288312,0.49516963093608557,0.0,0.0,249316.06,3.33369637792313,2550000
53
+ 0.020809721921458323,1000.0,0.0,112.39723954720726,0.7388310895636137,-307.2375235968068,0.009088951369598188,3.3906965967488585,0.21941215749711016,0.4899287611374205,0.0,0.0,249317.02,3.333581213556819,2600000
54
+ 0.020442893329002225,1000.0,0.0,112.57778120295796,0.7518656710788688,-307.0954273761041,-0.005951899846605828,3.0361009393054377,0.22186250312358094,0.5011803754761974,0.0,0.0,249328.36000000002,3.3335378114704906,2650000
55
+ 0.020467163142040477,1000.0,0.0,112.29844960986,0.7740204188996276,-306.98256073791396,-0.0009723833326995714,3.1316506983584413,0.22301804895877642,0.5033832050463499,0.0,0.0,249322.66,3.3350243551614187,2700000
56
+ 0.019900057897716674,997.96,20.297743716975045,111.46473534120432,3.023645853505455,-306.8415842126495,-0.005149833753705169,3.0822308545655064,0.22144956234663477,0.5003409184858212,0.0,0.0,249327.4,3.332960616385657,2750000
57
+ 0.020094513125792468,481.32,76.27658618475266,51.08160616591726,9.421878145949284,-307.1356784503162,-0.00025418030917648363,3.0021311197721783,0.22162673313826137,0.4999541561791369,0.0,0.0,249324.30000000008,3.3347668394367265,2800000
58
+ 0.019619134898073994,867.72,195.14502709523498,95.85144151960384,23.282530001573548,-306.7071489764371,-0.0026558974984288073,2.879633425162422,0.22557473669648287,0.5111934577760104,0.0,0.0,249324.31999999995,3.3340203488532794,2850000
59
+ 0.01928517261300231,1000.0,0.0,112.50966068634682,0.7754391207175467,-306.3316510284437,-0.005885864732116555,2.830977881696779,0.2265592074832306,0.511650627526051,0.0,0.0,249316.3,3.3332899603955393,2900000
60
+ 0.018911352694146382,1000.0,0.0,112.25197421386225,0.8069227786975275,-306.23230325866894,0.018068297323435317,3.0379687072253594,0.22753761566162092,0.5185162383842489,0.0,0.0,249326.86,3.3341269813814227,2950000
61
+ 0.018743230602927794,1000.0,0.0,112.20594927807316,0.820468662795535,-305.8774158343576,-0.03459411007963146,2.870039608088722,0.2313958851385119,0.5260487941661608,0.0,0.0,249331.4999999999,3.3335589982239147,3000000
hopper_medium_expert_sparse/mobile_based/neuralODE/seed_123&timestamp_26-0506-193304/record/consoleout_backup.txt ADDED
The diff for this file is too large to render. See raw diff
 
hopper_medium_expert_sparse/mobile_based/neuralODE/seed_123&timestamp_26-0506-193304/record/dynamics_training_progress.csv ADDED
File without changes
hopper_medium_expert_sparse/mobile_based/neuralODE/seed_123&timestamp_26-0506-193304/record/hyper_param.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"config": "config_gormpo/hopper_medium_expert_7_neuralode.yaml", "algo_name": "mobile_gormpo", "task": "hopper-medium-expert-v2", "seed": 123, "device": "cuda:3", "dataset_path": "/public/d4rl/sparse_datasets/hopper_medium_expert_sparse_78.pkl", "dynamics_path": "log/hopper-medium-expert-v2/seed_123&timestamp_26-0112-030632/model", "reward_penalty_coef": 0.3, "classifier_model_name": "/public/gormpo/models/hopper_medium_expert_sparse_3/neuralODE", "use_wandb": true, "wandb_project": "mobile-gormpo", "wandb_entity": null, "domain": "gym", "actor_lr": 0.0001, "critic_lr": 0.0003, "hidden_dims": [256, 256], "gamma": 0.99, "tau": 0.005, "alpha": 0.2, "auto_alpha": true, "target_entropy": -3.0, "alpha_lr": 0.0001, "deterministic_backup": true, "max_q_backup": false, "norm_reward": false, "num_q_ensemble": 2, "dynamics_lr": 0.001, "dynamics_max_epochs": null, "max_epochs_since_update": 5, "dynamics_hidden_dims": [200, 200, 200, 200], "dynamics_weight_decay": [2.5e-05, 5e-05, 7.5e-05, 7.5e-05, 0.0001], "n_ensemble": 7, "n_elites": 5, "rollout_freq": 1000, "rollout_batch_size": 5000, "rollout_length": 5, "penalty_coef": 1.5, "num_samples": 10, "model_retain_epochs": 5, "real_ratio": 0.05, "load_dynamics_path": null, "epoch": 3000, "step_per_epoch": 1000, "eval_episodes": 100, "batch_size": 256, "lr_scheduler": true, "penalty_type": "tanh", "density_model": "neuralODE", "target_dim": 14, "obs_shape": [11], "action_dim": 3.0, "max_action": 1.0, "classifier_type": "neuralODE"}
hopper_medium_expert_sparse/mobile_based/neuralODE/seed_123&timestamp_26-0506-193304/record/policy_training_progress.csv ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ alpha,eval/episode_length,eval/episode_length_std,eval/normalized_episode_reward,eval/normalized_episode_reward_std,loss/actor,loss/alpha,loss/critic,penalty/lcb_mean,penalty/lcb_std,rollout_info/dynamics_penalty_mean,rollout_info/dynamics_penalty_std,rollout_info/num_transitions,rollout_info/reward_mean,timestep
2
+ 0.25918114657774377,33.51,0.7415524256584966,2.3208645659624114,0.6571153701478841,-353.2125522837994,-0.9583648978661995,15.366632210261509,0.46442614146727523,0.6707110940538428,0.6170387219914739,0.34261708217826803,24927.700000000008,3.3115280578070205,50000
3
+ 0.12276836056664586,18.17,0.6489221833163048,1.3510916589815454,0.6576270403081053,-561.5034149017403,-0.04693270917709901,34.70464659656061,0.5032575760546326,0.9039036209073656,0.48960734888294205,0.35093886719463235,24928.699999999997,3.313979306752653,100000
4
+ 0.07374576026670694,40.8,0.7348469228349533,2.6605344589035336,0.6597410861907823,-363.17854362305116,-0.045776267434619704,11.199762955315022,0.2969513283574523,0.5227822068378294,0.24499547113461648,0.29980587259240477,24928.92,3.2940233936887418,150000
5
+ 0.05420930809319047,56.45,1.3219304066402287,3.810145636904626,0.7229289185480176,-309.31635692260505,-0.037414129085131205,7.505794430968714,0.21915202715575452,0.3879912507231535,0.17410814346518483,0.24991334850470603,24937.019999999993,3.304976113143057,200000
6
+ 0.04321059301868011,314.68,83.11400363356346,31.62078402997842,9.783026849795998,-296.18047868408325,-0.03789286652076983,6.182949322730144,0.20227165495366056,0.3776618696056353,0.12862278008427364,0.2215155148565396,24930.96000000001,3.305169239196707,250000
7
+ 0.03477302164871268,69.69,0.7168681887209113,5.039771524189965,0.667909726939398,-301.13886542297394,0.0019888707216829914,6.560717146909241,0.18618979764952887,0.3556654312741752,0.12979155638727377,0.21341034099894426,24931.83999999999,3.308351663306151,300000
8
+ 0.0348910246588291,968.7,111.02346598805136,102.48378619357909,11.930125315856378,-300.6076583355703,-0.010732879031077034,6.308025749133812,0.19296233073636973,0.39024170094131994,0.1146658975346866,0.20261165345710125,24932.2,3.3073367701367773,350000
9
+ 0.033624881133585444,49.06,39.642356135830276,3.33604049726708,4.86415334854178,-299.354231074216,0.007877846752591365,5.9267445544685025,0.19831635125607378,0.40622336292029004,0.10121043243883396,0.18691640759271944,24934.620000000006,3.304355662002792,400000
10
+ 0.033112660664878675,259.63,29.864579354144606,25.420405194154146,4.012084783662463,-298.5089934698519,-0.010838334277123217,6.210221809748479,0.2015664416727423,0.39101100897028807,0.10358927609314736,0.19085694117858662,24930.219999999994,3.3106160173767565,450000
11
+ 0.03063567495178419,256.75,40.98911440858414,26.340122469050915,5.387880231911469,-301.0778356146197,-0.0030082953656837175,4.507674188654496,0.1977812787464244,0.38133851685524217,0.11555902935314416,0.20880929834421275,24933.12,3.3147920297250013,500000
12
+ 0.028536928063817153,247.59,37.671234383810685,25.43183618182091,5.094807140195778,-305.9984489141835,0.006374309117980206,4.8089125064288964,0.19448290545001667,0.3797118431216458,0.12872829743368175,0.22217522900096506,24932.8,3.313986522026112,550000
13
+ 0.029523824678063255,319.11,0.6766830868286868,33.06113806832654,0.7014511990835283,-304.4306378369111,0.013778828677311158,4.315748533325171,0.20386913886219496,0.4091186948743449,0.09816593620682061,0.1834781347089847,24931.659999999996,3.311129869436445,600000
14
+ 0.029905439362786664,366.37,115.93926470355073,38.649812558066756,13.908547143496754,-302.1191816076687,0.0008625291710343976,4.780851337020452,0.21267299467801948,0.42159380907326877,0.0954396600799129,0.1796193059247292,24932.540000000008,3.3111889018417036,650000
15
+ 0.029323588329777054,1000.0,0.0,111.5129340304978,1.1064679990092414,-302.73567114563605,-0.00649723632905647,5.617324625787799,0.2099397032156586,0.42378276939839077,0.10062957738804229,0.1842474675350091,24930.879999999994,3.313433186352148,700000
16
+ 0.029061579588167324,129.12,0.604648658313239,10.701696770062927,0.6651733962739456,-303.39457177368365,0.01203288630142841,5.5883827079129205,0.21129366051241574,0.44128557682544073,0.08953473672995574,0.17556719181870048,24933.28,3.312268067970398,750000
17
+ 0.03008365216828882,1000.0,0.0,107.21222315000377,0.8671059789306202,-302.7049060638467,0.01787432326547795,4.6730001849364715,0.2113380652077487,0.4445407576513291,0.08734273659131957,0.17278059885906386,24931.200000000004,3.31346921417271,800000
18
+ 0.029722794564626932,386.17,215.80083665268768,39.85517357437723,23.956153695719415,-301.4729143646223,-0.0030943243113904944,4.288705344620954,0.21741467991292462,0.4485165235352497,0.08370780955113663,0.16787166610227888,24931.120000000003,3.3084135877100436,850000
19
+ 0.028963100514710047,378.14,95.8735646567916,40.671970886634824,12.081475096462608,-301.61891408508166,0.01200230656411501,5.134914833908187,0.2085818309465057,0.4434984765407466,0.0803056968720338,0.1632362096652587,24930.2,3.3099782736482015,900000
20
+ 0.028829011433832468,277.13,50.73256449264121,28.444458740087086,6.637260855390421,-302.7859991345197,-0.0048395842721313505,3.772353633716123,0.2084050048547979,0.44628164029776785,0.0791006211476556,0.16111549927587576,24931.08000000001,3.3124486186403783,950000
21
+ 0.029443022209033297,1000.0,0.0,112.01663426874433,0.9054941638243101,-301.7448769122307,0.003711129758022529,4.478864389996488,0.2195566255071766,0.4607955778765676,0.0806508606255947,0.16255720590340064,24931.439999999995,3.3146175422214124,1000000
22
+ 0.030011453664936055,1000.0,0.0,111.97013453132634,0.9856911793304368,-300.1119647998023,-0.010988229757547437,4.837016536185857,0.22294035117059804,0.45812372451096306,0.08984498218726725,0.17692398938696402,24928.34000000001,3.311961302613153,1050000
23
+ 0.029785932928510197,1000.0,0.0,111.06417294597617,0.7731610603767565,-300.1757933795182,0.009702127097696007,4.156713176136135,0.22058679254740501,0.4633813767418261,0.07875588520691744,0.1633902906970766,24933.1,3.3131157056025446,1100000
24
+ 0.030215778550729353,912.38,249.23116899778003,101.70137477348258,29.624158045351546,-302.1766916790672,0.003746459450200115,4.861645025123366,0.2169200762954361,0.4713706088772436,0.09092543508793141,0.1777618896456977,24931.7,3.3112195633705928,1150000
25
+ 0.029841387263015128,607.64,172.95817529102231,65.90103777105342,20.36158831824288,-300.7105619262719,-0.010170185144506485,4.09013612802625,0.2220185649272782,0.481343250717221,0.07619984448621739,0.1579236458368262,24928.84,3.312711162433224,1200000
26
+ 0.030182324878983216,1000.0,0.0,111.30525458962428,0.836275644611296,-301.48561410644754,0.041230205287710216,7.607625755734596,0.216499909008146,0.46761946023881057,0.08661788959334256,0.16668217704217506,24931.14,3.308494364617667,1250000
27
+ 0.029763336905911354,154.92,87.72088462846233,14.059577863386114,10.740878896933054,-299.9895716540504,-0.012150067091807656,4.200560633994346,0.23682601462155362,0.5187616329330222,0.08067504207221747,0.16175022139865944,24932.319999999996,3.307937168445712,1300000
28
+ 0.027980043484345202,1000.0,0.0,110.67228425991682,1.1393054079654878,-301.56353037719845,0.0034015893036125184,5.629465693147191,0.22411892105981643,0.49809061237931385,0.08804703738901237,0.16909669227344384,24932.06000000001,3.301994014829867,1350000
29
+ 0.02699937937621034,334.57,17.031884804683244,34.17737534982421,2.260690485097634,-302.04218955993434,-0.003706749726869109,3.430150557070979,0.21930220782503504,0.5034120709586121,0.0810604082743,0.16110318295839127,24935.32,3.306573173247491,1400000
30
+ 0.02738143166810261,538.84,470.4773686374298,58.10680446761862,53.795023191303095,-301.98597923095826,0.0014970772451909687,4.317972640571564,0.22537750593930492,0.5109951450711484,0.07733331476523961,0.15774876451394432,24930.519999999993,3.3066693540340117,1450000
31
+ 0.02773757624894385,294.67,177.64273444191292,29.19877979609688,19.747021181767273,-301.5463306518553,0.004379259425401394,5.841342661237796,0.22855688345909211,0.5241608250692482,0.07705193242119994,0.15766696245481274,24932.94,3.3039706170667564,1500000
32
+ 0.026729971616081982,1000.0,0.0,108.7329137666197,0.7458838363255089,-303.3985204278607,0.008493194938749428,6.167949611609066,0.2219720827490065,0.5079287206056786,0.08029738577667009,0.161109993014854,24934.94000000001,3.30823353170675,1550000
33
+ 0.024645801237076385,1000.0,0.0,109.06503385900285,0.9746412356583202,-305.1767218219008,-0.021784721521027287,4.0659624571883235,0.21351369599789502,0.4840553056585827,0.08056983837895378,0.1650199427846919,24932.419999999984,3.3113316448101324,1600000
34
+ 0.02511117705523968,1000.0,0.0,108.58808371168207,0.9540071264944469,-303.27407928711375,0.00572707003489112,5.034708965114332,0.2184958058243981,0.48434804922700353,0.08145884244471,0.1643924309294671,24929.040000000008,3.310267325852072,1650000
35
+ 0.024310725331343364,1000.0,0.0,110.52644793098064,0.8901482736483166,-303.81782572204327,0.014879092118814904,3.7762504062795825,0.22012107840657394,0.4934504490035764,0.07233028379093648,0.15495496231200429,24930.5,3.3136809409784163,1700000
36
+ 0.02461662262834615,1000.0,0.0,109.90368152328662,0.8713326478374975,-303.31369624938,-0.009104147022515354,3.7258586131084077,0.22263229627519923,0.5009940096536192,0.07557238204892766,0.15348824541840853,24935.340000000004,3.3027045242673703,1750000
37
+ 0.024362307343818508,1000.0,0.0,110.88272780099268,0.7208176495596942,-304.0629338165299,0.0298712870755794,4.722065662835844,0.21724157266348604,0.4848769691565675,0.07430375869838521,0.15786120484085364,24929.3,3.3146587619198526,1800000
38
+ 0.022896369595266614,1000.0,0.0,112.14836484397284,0.8723781954496811,-304.8938930249075,-0.01885804189987564,3.7197042847156463,0.21362059727788268,0.4707281912863239,0.07670113995932866,0.1633854393035147,24933.22,3.3164842381164084,1850000
39
+ 0.023756804846338582,1000.0,0.0,110.56028205115804,0.7327957046821046,-303.43977402221645,-0.0034142754788697763,3.579128540694674,0.22193917631715607,0.48245609606117,0.07492258908587031,0.15766402190129586,24931.260000000006,3.3105148431784617,1900000
40
+ 0.02248910583682362,996.84,31.44160301256919,110.84770282950646,3.7175367242620703,-302.6764507177716,0.005762755847499012,3.198959534275525,0.22085596669137425,0.473562865841988,0.07842486410996116,0.161374727207746,24934.319999999996,3.311750017067648,1950000
41
+ 0.024824660117626164,812.85,247.15717165399022,91.61179601223004,28.483162493909592,-302.6347744451882,0.02345007848583175,3.6381198971271713,0.2333437642985568,0.5069066915342151,0.07730531337988102,0.16160029235053472,24932.359999999993,3.306654196477702,2000000
42
+ 0.024004887616931928,1000.0,0.0,111.36836969930837,0.7781976288592442,-303.5923475872736,-0.012260510283671786,3.2703742340696045,0.22585756069421853,0.4834797056767337,0.08023867261390084,0.16336220670487256,24927.76,3.3051636211685453,2050000
43
+ 0.02637113286580897,1000.0,0.0,111.59187826599519,0.7508725579592703,-301.6857262896781,-0.005667623188569963,4.241718921818697,0.23734988167107268,0.5248960852721484,0.07733032885011305,0.16302244055560117,24934.699999999997,3.308556865484344,2100000
44
+ 0.02566022217206675,1000.0,0.0,112.33282509533609,0.7358289404663408,-301.63818154357375,-0.006212704675123185,4.060069611995365,0.23572600459843862,0.5315239546966596,0.07167953716009867,0.158613717014245,24931.7,3.3112771713231126,2150000
45
+ 0.024972884744256758,590.43,325.69578612564214,64.48691151282914,38.185524310861496,-301.52579794433484,0.014503249518200529,3.669737204617263,0.2344170870593217,0.512812603784198,0.0798575016821527,0.16604916035982306,24932.999999999996,3.3110791189743414,2200000
46
+ 0.024433228996768676,1000.0,0.0,112.47417598087345,0.7097752820090686,-302.45015708922807,-0.013397805403694675,3.165720048781632,0.2300068926543001,0.5066500693649109,0.08331180556787023,0.1718603322863923,24931.56,3.31065660208423,2250000
47
+ 0.023659569515250767,1000.0,0.0,111.87166394830683,0.7351737175523064,-302.69791370300203,0.014517806258350597,3.6255960737240738,0.2249868760380147,0.5033050021898774,0.07872313251068988,0.16441456819517639,24931.69999999999,3.309842428446189,2300000
48
+ 0.024504202901348575,741.9,289.584478175195,82.4124026807893,34.086716473034244,-303.44290758850326,-0.01443284698292607,4.310420925441973,0.22042352604627483,0.4859744159436222,0.08245832107194453,0.17368287379292568,24931.480000000003,3.318015620664361,2350000
49
+ 0.023561072922833336,1000.0,0.0,111.42455101668985,0.7505198969139283,-304.1892601245189,-0.0033740114016833295,3.4461792540431233,0.22040424567073671,0.48271329299211685,0.08166430137291772,0.171753018172812,24933.740000000005,3.3096604691266434,2400000
50
+ 0.02415502445012321,1000.0,0.0,111.61306574485556,0.7436465530922153,-302.78094626831313,0.03280077272638687,4.382362627040101,0.23150400431394494,0.504504599497614,0.0809715831773484,0.1690282648452534,24928.26000000001,3.310029564938514,2450000
51
+ 0.024072420433871398,1000.0,0.0,112.70311157652854,0.78727778890327,-303.8399157397458,-0.027173039270862957,4.6668550772797595,0.22102505227089045,0.4789349686503412,0.08384632989784206,0.17352949711697888,24932.06,3.3165104822291345,2500000
52
+ 0.02123912556033566,550.32,299.56791817549487,60.633899858670524,35.704560649984835,-303.4487670208777,-0.001327972682416809,3.1381507298922764,0.21594316744565975,0.46079481856018245,0.08281208976019315,0.17095443923405165,24930.98,3.3067288137009583,2550000
53
+ 0.022652383782714808,1000.0,0.0,112.42833006279429,0.7209344994780292,-303.76540512573484,0.022840306749716432,4.712897354910386,0.21792568210303795,0.4676996803373086,0.0841106667371591,0.17410651124405727,24929.380000000005,3.3096240177546132,2600000
54
+ 0.021253264939896807,956.99,115.32696952577918,108.899372103106,12.835390946364415,-303.8588971386717,-0.03356343185096936,3.1692902094911894,0.21156848533868883,0.4556414620020995,0.0766080957136491,0.1646037559202464,24930.179999999997,3.3109573833997934,2650000
55
+ 0.021767905870303465,1000.0,0.0,111.84291015737489,0.7439970290089476,-300.8251097576898,0.004963790116310112,3.8047963013267285,0.22470780326664486,0.4793393526470658,0.07546423872210414,0.16138835879339372,24927.74,3.3091859752232864,2700000
56
+ 0.02116438143994645,1000.0,0.0,110.68190537661364,0.7281195899890044,-300.51625865906107,0.03639070186585202,4.1379274788725064,0.22841037025391928,0.5011694548651511,0.07449094462816551,0.15908740530691004,24933.48000000001,3.302396804985382,2750000
57
+ 0.02056224993906916,889.36,179.1265206495119,99.44584868187012,21.400744090715985,-300.7989757727041,-0.07706001163885089,2.7779777691030296,0.22134619525089888,0.4708725098213549,0.07517342466796267,0.16204027677822133,24932.219999999998,3.3054393340737125,2800000
58
+ 0.019265027996320357,1000.0,0.0,112.50715844483057,0.7399974581324944,-299.66447000427013,-0.013173190618903137,3.589998765149126,0.2313171557462216,0.4922246263670908,0.07114622162649496,0.15482869976886696,24932.24000000001,3.3058149391754132,2850000
59
+ 0.019196306787747728,913.22,194.39776644807418,102.68621869796885,23.304929365468084,-299.54428383606154,-0.018232655069453776,3.2969900102710743,0.23732054419934762,0.5217177753138452,0.07027666073819384,0.15325924087215126,24933.359999999986,3.297526638026353,2900000
60
+ 0.021708716516271202,1000.0,0.0,112.78632981055428,0.7265878853052876,-296.33758520568824,0.06303986219436053,3.7223768968212703,0.25889579204410135,0.5826486237177393,0.07092239416233852,0.15167467539584162,24931.980000000014,3.291537558899747,2950000
61
+ 0.010170010957923007,1000.0,0.0,113.02338317622336,0.7143595416612519,-295.0099958612059,-0.25460766580745137,3.2202095889282494,0.2592366433504194,0.5731380504456199,0.06944857523260464,0.15040299086396586,24933.25999999999,3.2926897406367552,3000000
hopper_medium_expert_sparse/mobile_based/neuralODE/seed_42&timestamp_26-0506-193304/record/consoleout_backup.txt ADDED
The diff for this file is too large to render. See raw diff
 
hopper_medium_expert_sparse/mobile_based/neuralODE/seed_42&timestamp_26-0506-193304/record/dynamics_training_progress.csv ADDED
File without changes
hopper_medium_expert_sparse/mobile_based/neuralODE/seed_42&timestamp_26-0506-193304/record/hyper_param.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"config": "config_gormpo/hopper_medium_expert_7_neuralode.yaml", "algo_name": "mobile_gormpo", "task": "hopper-medium-expert-v2", "seed": 42, "device": "cuda:2", "dataset_path": "/public/d4rl/sparse_datasets/hopper_medium_expert_sparse_78.pkl", "dynamics_path": "log/hopper-medium-expert-v2/seed_42&timestamp_26-0112-030627/model", "reward_penalty_coef": 0.3, "classifier_model_name": "/public/gormpo/models/hopper_medium_expert_sparse_3/neuralODE", "use_wandb": true, "wandb_project": "mobile-gormpo", "wandb_entity": null, "domain": "gym", "actor_lr": 0.0001, "critic_lr": 0.0003, "hidden_dims": [256, 256], "gamma": 0.99, "tau": 0.005, "alpha": 0.2, "auto_alpha": true, "target_entropy": -3.0, "alpha_lr": 0.0001, "deterministic_backup": true, "max_q_backup": false, "norm_reward": false, "num_q_ensemble": 2, "dynamics_lr": 0.001, "dynamics_max_epochs": null, "max_epochs_since_update": 5, "dynamics_hidden_dims": [200, 200, 200, 200], "dynamics_weight_decay": [2.5e-05, 5e-05, 7.5e-05, 7.5e-05, 0.0001], "n_ensemble": 7, "n_elites": 5, "rollout_freq": 1000, "rollout_batch_size": 5000, "rollout_length": 5, "penalty_coef": 1.5, "num_samples": 10, "model_retain_epochs": 5, "real_ratio": 0.05, "load_dynamics_path": null, "epoch": 3000, "step_per_epoch": 1000, "eval_episodes": 100, "batch_size": 256, "lr_scheduler": true, "penalty_type": "tanh", "density_model": "neuralODE", "target_dim": 14, "obs_shape": [11], "action_dim": 3.0, "max_action": 1.0, "classifier_type": "neuralODE"}
hopper_medium_expert_sparse/mobile_based/neuralODE/seed_42&timestamp_26-0506-193304/record/policy_training_progress.csv ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ alpha,eval/episode_length,eval/episode_length_std,eval/normalized_episode_reward,eval/normalized_episode_reward_std,loss/actor,loss/alpha,loss/critic,penalty/lcb_mean,penalty/lcb_std,rollout_info/dynamics_penalty_mean,rollout_info/dynamics_penalty_std,rollout_info/num_transitions,rollout_info/reward_mean,timestep
2
+ 0.2258456306674359,39.86,0.6636264009214823,2.6801365170179756,0.6573738107597223,-299.6788204209075,-1.1854367235663064,12.043195537928824,0.34799668861165595,0.5380103178127252,0.5182002151703723,0.3460159443271164,24930.58,3.307488215561325,50000
3
+ 0.058888256052061945,69.8,0.8602325267042626,4.984025321118811,0.6835317549701229,-357.8975104949967,0.015405668899752445,11.128962836992736,0.2592937078028934,0.5268806466293332,0.23668124180114894,0.2936878556446719,24934.02000000001,3.327748606791136,100000
4
+ 0.04699588350094824,69.32,0.823164625090267,4.941833045273882,0.6786859758901974,-323.7621097100802,-0.035460509305857466,6.751072914948369,0.2160352012181296,0.3856133226719502,0.17641550554086702,0.25876898791783887,24932.359999999997,3.320444255081439,150000
5
+ 0.03885389479763779,226.88,23.633992468476414,21.52724304337388,3.6215496011142574,-310.74677978332494,-0.021612899845168003,6.435906578502738,0.19015338577285446,0.3476030770568579,0.15597358773625045,0.24828280314874523,24931.220000000023,3.309555235711933,200000
6
+ 0.03758728018574383,278.54,13.706509402470056,31.169634754882026,2.119219702518335,-308.4798962310794,0.003622434061542183,7.526953316041197,0.18536963542968,0.3655441103485221,0.1328283758783344,0.21887531078023448,24929.899999999994,3.313721175158217,250000
7
+ 0.0323015032347657,32.61,0.7469270379361025,2.0280770647489508,0.6662816769822769,-314.08651517272665,-0.021630454853065566,6.21893306811215,0.18051346771999946,0.34664064738437433,0.150805581340462,0.23932778814187877,24931.39999999999,3.3242228913974197,300000
8
+ 0.02988067314334229,349.24,3.8499870129651095,38.64770234514376,1.1430255138855032,-315.87726228820816,-0.004179571354836121,5.428145791667698,0.17652178696304338,0.352282251963018,0.13531236135457994,0.23511451891673577,24931.16000000001,3.3268474146191997,350000
9
+ 0.03148031101789335,953.36,88.49932429120577,105.47448483563468,9.991417986988997,-310.13631890746245,0.013090383820607794,6.7027481502807245,0.18709402115881385,0.38269954751312635,0.11578283147791626,0.21028658539263137,24933.96,3.32445705678918,400000
10
+ 0.029457563273571134,134.4,0.8717797887081349,10.609222991513386,0.6815432645980141,-308.2647789605687,0.005914399566426829,4.75162048463581,0.18339073393568306,0.3772325242172144,0.08641906584253112,0.1802554782576746,24934.400000000005,3.3232117494206,450000
11
+ 0.030254013261050067,732.66,356.2160080625237,81.5603781798231,41.348486997255215,-306.2345663598601,0.001432985040508492,6.536201729377496,0.19181496841982107,0.4032971495944227,0.09276991527654302,0.18781928292651864,24929.66,3.330885068041893,500000
12
+ 0.030491294468976363,37.98,0.7208328516376039,2.3700162160197014,0.6735046206866848,-305.87413389404674,0.02172520761869921,5.886308875045725,0.19350452386662398,0.4039399041332296,0.07847647626328684,0.16261162238996052,24929.819999999992,3.318031957525764,550000
13
+ 0.03053435780983404,213.55,0.6538348415311009,20.27243325900148,0.6874553069147136,-306.79159581237656,-0.0014276493836568379,6.377165823223623,0.19625736023813345,0.4068861639389377,0.08812262896978167,0.1720909869789218,24932.50000000001,3.315011342585824,600000
14
+ 0.03101497961480173,220.73,0.6611353870426239,21.241174910140458,0.6742842884967664,-308.81366999755596,0.03062680680565495,6.47199969762923,0.20460768032193224,0.43467576795429036,0.09574309342073115,0.18316104099059186,24932.12000000001,3.3143454885069827,650000
15
+ 0.030239377189576356,1000.0,0.0,109.52597311705772,0.8358485499098731,-310.46875443664686,-0.021542131012752538,7.231007828410917,0.19953129980102152,0.42646424126892835,0.106368496443206,0.19439777279185752,24933.899999999998,3.3093913245179705,700000
16
+ 0.027684712930545103,1000.0,0.0,112.14264752617026,0.7400991307649145,-313.34833333068497,-0.0074006597163530806,4.745067077350573,0.1853929578998686,0.3921704263749736,0.09416859255165129,0.18794213921766528,24931.460000000006,3.3171198949299785,750000
17
+ 0.027142636915482417,29.62,0.5617828762075256,1.8985510861698423,0.6570087122785937,-312.37311474487143,0.02806375121608391,4.9791487371504,0.1915948549723628,0.4127611387661075,0.09036270934691085,0.1794395092120922,24932.44,3.316854572181849,800000
18
+ 0.033173835299126854,1000.0,0.0,111.88198425998783,0.7378798030999678,-309.4762066680872,0.02042819053456261,6.74957754982357,0.2152330306494243,0.4760402416858027,0.09055987265256685,0.17606818063829827,24930.799999999996,3.3135204388453854,850000
19
+ 0.030064458985254106,130.47,1.7632640188014952,10.9515120563954,0.8200539270594323,-309.67414524658665,-0.0026682532857732577,6.61064317119703,0.20825686289012532,0.45247322965800785,0.08525353598719917,0.17137600084898827,24933.36,3.314989109807164,900000
20
+ 0.027374614597745324,142.71,285.77597152314956,13.949444119738624,33.52577010203195,-308.77462338928694,-0.014498308651670757,4.92931059000607,0.20869982709467647,0.4731703775221132,0.07878494371760109,0.1667242012564609,24931.520000000008,3.3147522865259815,950000
21
+ 0.027775179872289165,36.3,0.458257569495584,2.2869443314722,0.6525941976636837,-310.03672358886877,0.0082823714860528,5.383608647352395,0.20741244331926234,0.4613557691794643,0.08049484305176628,0.16714235733742672,24930.6,3.3173253357572636,1000000
22
+ 0.02809660524729654,1000.0,0.0,111.70104699299179,0.9376334777251586,-309.3111672100729,0.005453139897510493,5.109047813130552,0.2127545126083515,0.4747569438764454,0.07861261422144074,0.16840243768871074,24930.140000000014,3.3155400364463663,1050000
23
+ 0.027219430614411712,882.0,196.55742163551088,100.81200872097608,23.372586232431324,-309.4420331457509,0.01469622453451155,4.7134508527302685,0.21230811974435823,0.47713710540324333,0.07729924420457468,0.16274776505533536,24935.08,3.311432120915049,1100000
24
+ 0.029391702935956634,1000.0,0.0,111.82775584597317,0.7266993851757589,-309.8122658190935,-0.004002378190905013,5.758250518529481,0.21572682406634003,0.47489787117391474,0.08783350246340815,0.17626516730257802,24935.060000000012,3.3172526945570255,1150000
25
+ 0.026468688644096214,33.86,0.6003332407921453,2.1559315204042484,0.6620153207318794,-309.5329289599566,-0.005131787426397304,4.9990158216214216,0.20372405478745917,0.4542576263129722,0.07439590881977336,0.1582420742642307,24934.52,3.307442051752846,1200000
26
+ 0.026965531476549728,989.46,64.90368556561329,111.46708082182421,8.263356539434982,-308.99765230651514,0.03153226497061472,6.488298676023567,0.21389949352786014,0.4809283023476567,0.08364636152305756,0.17047637328152787,24931.999999999993,3.3113564533001965,1250000
27
+ 0.025502970197349966,281.28,1.312097557348538,28.537796785005355,0.7357053325355408,-309.7229638128624,-0.005912597668878734,4.521487526104511,0.20578569822430945,0.4542045166397091,0.07702594458157092,0.16733075703173667,24935.43999999999,3.311397842947379,1300000
28
+ 0.0238089209061486,459.29,147.13240941410564,52.364795380179,18.373603604640305,-311.30745626098565,0.0011895790114257207,3.8133062402117592,0.19991172556013037,0.4454736325512806,0.07403814633340462,0.15929783599092237,24933.599999999995,3.312426572047144,1350000
29
+ 0.025457839484512777,139.28,1.1320777358467924,11.539929675932209,0.7049904909132313,-309.38061037109355,0.013221249160989847,4.876574774194945,0.21332224625274632,0.48723576280951814,0.07568269485118817,0.16154131571106775,24931.9,3.309572223659952,1400000
30
+ 0.024007459170818347,566.68,225.02457110280204,64.46080102568594,27.286005470836795,-310.05302417846775,-0.016738862012475753,3.8012947277773037,0.1979966150853032,0.4464133670097587,0.07226236843902469,0.15620075223799454,24934.520000000008,3.3169888851093785,1450000
31
+ 0.025150762827210196,995.8,21.686862382557788,112.76752529871952,2.2951792589960704,-310.9481227563479,0.008309585742205743,4.3728614055002,0.20475985031277047,0.46412718215465976,0.07148753449922629,0.15454587617346172,24932.14,3.315871417689035,1500000
32
+ 0.024770723709650683,896.07,281.44385781182007,99.51473069241864,33.30795949482396,-311.07536210998643,0.0020240771286186886,4.36100630225897,0.20076835916385308,0.4505803562009305,0.06441527992916793,0.14591777080124718,24933.600000000006,3.315159064392781,1550000
33
+ 0.026060282119996624,994.25,40.317583012874174,107.55733751949417,4.072724826655998,-310.19734709777975,0.033061218591705285,5.476284162970853,0.2060358058233584,0.4687360598403208,0.06745787555931206,0.1495896767160199,24930.22000000001,3.3141175621203502,1600000
34
+ 0.026163366215899674,927.39,104.15929099221059,105.68558179534516,11.25484859992102,-309.7224745873966,-0.02111673990838175,4.1225758562361685,0.20737825898781356,0.47807909592449543,0.0672201734487931,0.1517144005064544,24932.180000000008,3.3161654056838628,1650000
35
+ 0.026689322055838995,452.29,99.13761092542023,52.80982504258988,12.405720751977482,-308.5288422613501,0.020233914910442963,4.630374137477932,0.21224913886308813,0.4968277015298597,0.06260976560039924,0.14632619026738253,24929.8,3.3180585729608305,1700000
36
+ 0.026754137742221185,1000.0,0.0,110.77460249970883,0.7580921667174155,-308.86565208435155,-0.0004470066962387997,4.530243256135036,0.2100499039429429,0.47750389773845286,0.07211171652877071,0.15771687484410216,24935.039999999994,3.3142152681496726,1750000
37
+ 0.02727342507280431,1000.0,0.0,110.90727976951828,0.7511655879711387,-307.6852235247758,-0.009936623432487367,4.8774780299197875,0.21514788392543624,0.4923064844003276,0.07395539286319369,0.1597940587107009,24932.439999999988,3.315971393100815,1800000
38
+ 0.02520015912022443,1000.0,0.0,111.55819669704175,0.8389514596445071,-308.7029341925016,-0.005739220445900896,4.791883590575466,0.21016174318343772,0.47374522419244436,0.0720005350147905,0.1585771412482071,24934.60000000001,3.312528546647719,1850000
39
+ 0.024629589398205243,1000.0,0.0,112.61720930668008,0.7286768695647113,-309.4147457415785,0.014758989684171827,4.288397209477526,0.20522542239918992,0.4560991075216234,0.07320586086593486,0.15844970679992892,24932.580000000005,3.318498339959099,1900000
40
+ 0.02635809200845672,1000.0,0.0,111.90505084396922,0.7259490891535031,-308.115274558716,-0.008030326026678017,4.687913671073973,0.21874239009588886,0.4991036604142198,0.06789718773401322,0.15151917320411765,24932.68,3.3149235543247957,1950000
41
+ 0.023953664579242313,1000.0,0.0,112.09543396660528,0.8549167305698189,-309.21330801635634,-0.020786605557799428,3.127693909162301,0.20402101084411117,0.45003637442708,0.06324080847997181,0.14478135359029093,24935.37999999999,3.3116979632210057,2000000
42
+ 0.023308869848028265,1000.0,0.0,111.88451909540052,0.7690464595146344,-309.87575858581675,0.005351241082623739,3.512326968365905,0.20863546379387443,0.4740230157390249,0.05998702967959526,0.14032262867643833,24934.28,3.311115240589779,2050000
43
+ 0.02270848246403027,495.49,204.2504587510148,53.92445847801841,24.309698519420163,-309.6269214617952,0.0158969823396204,3.913173352589594,0.20795307685092312,0.4685385804697844,0.060520297623447426,0.1383852431566961,24927.26000000001,3.3077056016279607,2100000
44
+ 0.023877958037368963,711.41,239.94228868625888,82.48069277208538,27.75431113486782,-309.19648393555127,-0.003697937899231763,4.624471005389736,0.2093478946341538,0.4695205335381595,0.06889282521215245,0.1525762912456265,24933.69999999999,3.312581918184152,2150000
45
+ 0.02373974987983676,994.03,27.281662339381004,112.7066199437557,3.447463963732669,-309.16728987366264,-0.016803309400007488,3.7146252128231536,0.2120670836792886,0.4683995936706646,0.06880390969240996,0.1549599318403383,24933.68,3.3137290626433256,2200000
46
+ 0.023444539679735994,129.0,0.848528137423857,10.807724144385583,0.6837535811946807,-309.47758731567245,0.027884873776361358,3.8481081428962685,0.20779385616645116,0.46049281631767897,0.06823640776340748,0.1514447447670264,24933.440000000017,3.3193514273773372,2250000
47
+ 0.022024396543204757,1000.0,0.0,112.37610640829942,0.8026873181239473,-309.7596379644714,-0.018739382575154378,3.5915197800743575,0.20391479647591912,0.45267659265667287,0.06606508366750406,0.14683770299107451,24932.700000000004,3.3186582826030775,2300000
48
+ 0.022935505227334868,1000.0,0.0,112.74399747973649,0.9185026798371918,-309.80749393555305,-0.0015786478803307242,4.249650074589235,0.21108160640761378,0.465705039548873,0.07181208284067885,0.15596486183298633,24932.160000000003,3.316732029412802,2350000
49
+ 0.02281355710424447,889.06,161.3357257398373,101.48589028741367,18.958481607548762,-309.60841259887644,-0.0048004522542652575,3.4844416580569866,0.2102705544939632,0.4629924576085809,0.0631318562768534,0.1417698504927772,24936.079999999994,3.316390396100234,2400000
50
+ 0.02220853676404805,41.15,5.505224791050772,2.616030100980346,1.0397976265654871,-309.1931708166408,-0.008715561204552127,3.256948326784365,0.2124364850589636,0.46704048280209237,0.06818932484107826,0.14617002302475285,24931.320000000007,3.311784532582159,2450000
51
+ 0.021354673795178403,970.39,121.4900732570361,110.54236417233882,14.474879344919092,-309.71664547546476,0.05706627931330346,3.2620387464702083,0.2041345821988599,0.44795986117661163,0.066630766268977,0.14595893024221418,24935.019999999993,3.310921128435025,2500000
52
+ 0.02362681289885215,1000.0,0.0,111.94520014566575,0.726152753611345,-307.6635618322747,-0.03505358020033702,4.461073445932902,0.22468353191286783,0.49368267810105865,0.06330472355423464,0.14152967011690662,24932.699999999993,3.3156629508490263,2550000
53
+ 0.022506332539282414,1000.0,0.0,112.87862935889899,0.804360984565266,-307.7558164984127,-0.004739455841928688,3.418263467049583,0.2167478751015656,0.4683011147102719,0.06446965304425233,0.1427051961829106,24930.8,3.3140817983898327,2600000
54
+ 0.020545595917552947,975.97,105.1811252079003,111.46246246891889,12.305152987680161,-309.1718116827361,-0.017295724236816246,2.83455821402069,0.2130877358403799,0.4769312870070338,0.06687622624819392,0.14647425750462234,24931.4,3.3150357650253643,2650000
55
+ 0.02015102148774973,1000.0,0.0,112.94132104630867,0.8365086958442988,-308.1013659527546,0.00046120491784059714,3.3002652890348663,0.21427298471033615,0.47852226392656877,0.0635373021390978,0.14316322339515616,24927.92,3.316965740398689,2700000
56
+ 0.02085376532338558,994.29,32.25098293075731,112.5234600376474,3.728107725699667,-306.981334644164,-0.00023967422448123048,2.8252155534732033,0.2225982364463809,0.4954127394583776,0.061847822298983696,0.14029387573209437,24932.48,3.3117945547720895,2750000
57
+ 0.020815888213179704,1000.0,0.0,112.8494821979765,0.762411767683013,-306.2317839111371,0.012035706035121736,3.5956734534835646,0.22275360390275575,0.5002539313170284,0.06331191404425242,0.14172157951989964,24933.48,3.315466932925399,2800000
58
+ 0.020946938813589673,1000.0,0.0,113.34729970245255,0.7364907234855274,-306.42618238892044,0.0019484396434576669,3.5144526449716302,0.21937917446940836,0.4859528314888502,0.0619811316060012,0.1424970503710849,24930.58000000001,3.3163356027043145,2850000
59
+ 0.020857007502764507,1000.0,0.0,113.27819285765526,0.7524763503214273,-306.00627351806276,-0.033773912891298684,3.4337086047470526,0.22555625375956348,0.5009635012859075,0.06211682061618583,0.14398438530014931,24931.180000000008,3.3164815703911543,2900000
60
+ 0.021296295407339703,1000.0,0.0,113.42020652633225,0.8023242953184456,-302.8249012823528,0.06105928321815949,4.6147950165093015,0.24220545442015048,0.5329860831424504,0.06500896882381868,0.15013257426214227,24932.739999999994,3.3164391862344926,2950000
61
+ 0.028431823503449655,1000.0,0.0,113.5318741921964,0.7641174660236796,-298.5965417150928,0.03462500699289108,5.399547384066598,0.2613980780914422,0.5744892689105771,0.0627680630856926,0.1469333341127084,24932.81999999999,3.316039558713078,3000000
hopper_medium_expert_sparse/mobile_based/neuralODE/seed_456&timestamp_26-0506-193304/record/consoleout_backup.txt ADDED
The diff for this file is too large to render. See raw diff
 
hopper_medium_expert_sparse/mobile_based/neuralODE/seed_456&timestamp_26-0506-193304/record/dynamics_training_progress.csv ADDED
File without changes
hopper_medium_expert_sparse/mobile_based/neuralODE/seed_456&timestamp_26-0506-193304/record/hyper_param.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"config": "config_gormpo/hopper_medium_expert_7_neuralode.yaml", "algo_name": "mobile_gormpo", "task": "hopper-medium-expert-v2", "seed": 456, "device": "cuda:4", "dataset_path": "/public/d4rl/sparse_datasets/hopper_medium_expert_sparse_78.pkl", "dynamics_path": "log/hopper-medium-expert-v2/seed_456&timestamp_26-0112-030630/model", "reward_penalty_coef": 0.3, "classifier_model_name": "/public/gormpo/models/hopper_medium_expert_sparse_3/neuralODE", "use_wandb": true, "wandb_project": "mobile-gormpo", "wandb_entity": null, "domain": "gym", "actor_lr": 0.0001, "critic_lr": 0.0003, "hidden_dims": [256, 256], "gamma": 0.99, "tau": 0.005, "alpha": 0.2, "auto_alpha": true, "target_entropy": -3.0, "alpha_lr": 0.0001, "deterministic_backup": true, "max_q_backup": false, "norm_reward": false, "num_q_ensemble": 2, "dynamics_lr": 0.001, "dynamics_max_epochs": null, "max_epochs_since_update": 5, "dynamics_hidden_dims": [200, 200, 200, 200], "dynamics_weight_decay": [2.5e-05, 5e-05, 7.5e-05, 7.5e-05, 0.0001], "n_ensemble": 7, "n_elites": 5, "rollout_freq": 1000, "rollout_batch_size": 5000, "rollout_length": 5, "penalty_coef": 1.5, "num_samples": 10, "model_retain_epochs": 5, "real_ratio": 0.05, "load_dynamics_path": null, "epoch": 3000, "step_per_epoch": 1000, "eval_episodes": 100, "batch_size": 256, "lr_scheduler": true, "penalty_type": "tanh", "density_model": "neuralODE", "target_dim": 14, "obs_shape": [11], "action_dim": 3.0, "max_action": 1.0, "classifier_type": "neuralODE"}
hopper_medium_expert_sparse/mobile_based/neuralODE/seed_456&timestamp_26-0506-193304/record/policy_training_progress.csv ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ alpha,eval/episode_length,eval/episode_length_std,eval/normalized_episode_reward,eval/normalized_episode_reward_std,loss/actor,loss/alpha,loss/critic,penalty/lcb_mean,penalty/lcb_std,rollout_info/dynamics_penalty_mean,rollout_info/dynamics_penalty_std,rollout_info/num_transitions,rollout_info/reward_mean,timestep
2
+ 0.23070886066630153,57.22,1.1625833303466895,3.919593825373123,0.7095999917470655,-290.4867709522532,-1.3561325981634689,11.487293790094734,0.36585205542354654,0.5276836088709195,0.49323878606058696,0.35416712667376327,24925.499999999993,3.3134296449536444,50000
3
+ 0.07950527871877014,41.28,3.190861952513772,2.6141527418306088,0.8845632715129771,-419.4616287298568,-0.0007166647314281159,17.574669705219208,0.344852942461669,0.6163367334511782,0.3630502463634987,0.36022670268904655,24932.500000000007,3.3173292577846714,100000
4
+ 0.06318754241131372,70.28,0.7756287771866126,5.043436885778545,0.6763413790109037,-397.1743670825223,-0.030711194406449427,13.221137838091657,0.27668108046799345,0.5458168249940826,0.2603316395947847,0.3299656705267664,24932.399999999994,3.3295049692706487,150000
5
+ 0.050689219197034764,70.39,0.6307931515164064,5.055940843833219,0.6664555340105764,-386.9652889013696,-0.015283133879006114,11.094939125638122,0.24477606902062726,0.526233440858133,0.22610742412890802,0.30786841752242844,24937.36000000001,3.3363240612861267,200000
6
+ 0.04330851941429086,18.6,0.5291502622129182,1.2841168930634146,0.6507035795321119,-343.4147506359879,-0.033909552488922655,9.524886498241516,0.20635926808968297,0.3995295793043078,0.19909796511190572,0.28279831960015006,24932.720000000005,3.326601082020881,250000
7
+ 0.04244705228313787,655.18,408.9483434371632,69.56812288761655,45.47940937491707,-304.379962512818,0.005930320672951245,7.413683328558315,0.19295689022049142,0.3424432097032635,0.1235262438809899,0.20695416076277548,24932.18000000001,3.3072278847283987,300000
8
+ 0.04047161817744385,37.04,0.5986651818838306,2.3349733653345988,0.6629972376728586,-293.74392041565727,0.0174275190099327,7.8010311976183,0.19466069962099267,0.3472881777460912,0.10499577540964622,0.18764169780430123,24930.98,3.3204242760612788,350000
9
+ 0.04121397370345982,13.39,0.4877499359302879,1.069078772936709,0.6476923670467871,-292.8683768035896,-0.01319096337974061,8.680643518397881,0.21265834357559907,0.3973585843470667,0.10272638426125859,0.18474783849478774,24932.08,3.3157820392696156,400000
10
+ 0.04013938520051517,36.38,0.7318469785412796,2.2880456261185107,0.6679275578936802,-294.34962079468016,0.0027095986513048153,8.23921281895272,0.21427444980561766,0.39667871571033847,0.09915985842401498,0.18002445073351675,24933.699999999993,3.310826826723637,450000
11
+ 0.03739354292064908,71.95,36.3902115959773,5.240262612948386,4.0250442000759366,-296.7444846411138,-0.0077913188071548735,5.569086920458029,0.20756217545896632,0.39775433930545545,0.08822614279318108,0.1683698135690018,24923.92,3.305095373610262,500000
12
+ 0.03570213434204479,59.18,30.07503283456229,4.09441094830419,3.4513457349725836,-298.3484459069858,0.002805307344310146,5.752747281501328,0.20797835088759653,0.4034876950109048,0.08406133777757034,0.1657652237797224,24931.49999999999,3.3044447476302468,550000
13
+ 0.03551195649608993,1000.0,0.0,109.88669838695404,0.8667649165668891,-298.5561475885001,-0.010054815131351494,5.694399383254059,0.21286255271851914,0.41902793892324014,0.08196437522674951,0.16286248285144506,24933.66,3.3121026379015777,600000
14
+ 0.03294376703016388,124.31,0.702780193232564,10.344686175553235,0.6850971008453476,-301.3788776538051,0.0024017191725222878,5.035266688733112,0.202698190953135,0.402832696068289,0.08722638276662538,0.17014802093610895,24932.36,3.3129655341668016,650000
15
+ 0.032820655836426654,797.31,207.67713860702148,89.82314792782348,23.502127134618508,-301.8459960528543,-0.00862174057565645,5.089433824504665,0.20233994412675727,0.4105405639445864,0.07982606050792142,0.16285874569711375,24935.339999999997,3.303216681294502,700000
16
+ 0.031521669705287,724.73,299.20878513172033,80.37172422197347,35.14799490805978,-302.93004207336577,0.00342473837386813,3.8643999922168883,0.19984988521843863,0.4065567165905317,0.07388251041442705,0.15952962039027477,24933.17999999999,3.319473626243134,750000
17
+ 0.03296095368538,955.14,118.87413680023084,107.20333317196516,13.705279216441088,-305.7417269964569,0.06338902949511935,9.812367200241068,0.19702010710209683,0.3992987935213757,0.09318745525197296,0.18039898686335198,24930.960000000003,3.3244947785991488,800000
18
+ 0.03142156354088349,842.02,315.96031333064604,93.16298677690271,37.09181590951309,-305.93032431579826,0.010977940797209401,4.52942589143161,0.19959049922779235,0.41637212336092844,0.08109240088444361,0.16947258431624762,24928.63999999998,3.3198709433878864,850000
19
+ 0.029103705139905327,984.22,110.46000000000001,109.52360210708494,13.414378123299423,-305.20935642943783,-0.0014494842506946797,4.086264269824052,0.20653714875310833,0.43456465503870817,0.08165996364451225,0.1728127154864102,24932.859999999997,3.3148307037021594,900000
20
+ 0.029231750302314518,37.38,0.4853864439804638,2.285122987414785,0.6538127060168852,-308.851241148069,-0.007286975732743782,4.255804056525279,0.1921887982009378,0.397345212750736,0.09338707465046699,0.18504794129147942,24935.579999999998,3.3195167711526246,950000
21
+ 0.030536539858430467,41.81,0.39230090491866065,2.6650234637330716,0.6416169628711037,-306.7626031292738,0.033820863059795966,4.643306664761338,0.20552420833840987,0.42937398876994826,0.08073078403535743,0.16740384051786766,24934.560000000005,3.3146076853013233,1000000
22
+ 0.03089987097762548,45.14,1.1577564510725045,2.810128696418676,0.7095963314561667,-304.3447449041756,-0.005625036978796071,5.039322132003926,0.20994973968535513,0.4372539730885635,0.08038846694160662,0.16586836680366376,24931.12,3.3201076595613332,1050000
23
+ 0.03054817503888189,49.94,0.23748684174075835,3.191824062095358,0.6416188820448261,-304.61722129151144,-0.0031683390321953775,4.264361716569678,0.21190112088427088,0.4448110023915795,0.08197983922991475,0.1684724963927226,24932.819999999996,3.3166304373828233,1100000
24
+ 0.0288754550352693,1000.0,0.0,112.07217625448594,0.9690070290780922,-306.184928352659,-0.0055575778120009415,3.9422389352536094,0.20563612691238514,0.43144550013244237,0.07736460474980855,0.16514755023120317,24930.95999999999,3.3187826994639273,1150000
25
+ 0.02999181700602177,1000.0,0.0,111.89407826846201,0.7359947383650237,-308.1574671173174,0.02966422930307715,4.908996507633903,0.205460085202904,0.4272916291078961,0.07347299872900212,0.15882918818635663,24930.14,3.3196194479635186,1200000
26
+ 0.03188270998794613,672.29,446.59353544358424,72.46358791336579,50.627179623987786,-306.77289885680597,-0.01121949452295904,5.364083000830397,0.2113226431386175,0.44047896576553197,0.07222567705412435,0.159748488539133,24934.200000000004,3.3247052119184892,1250000
27
+ 0.028008585540652182,1000.0,0.0,110.85980857497995,0.8551138296260528,-307.4868850909472,-0.007119823855087497,4.697868684321667,0.20143104562029254,0.4175863062308699,0.08128394578813805,0.17202810349492267,24931.54,3.328055935104957,1300000
28
+ 0.028404901615865286,1000.0,0.0,110.94760009343312,0.7898682936166567,-306.0231599810817,0.011094758056774713,4.64803508224481,0.21742944896936758,0.4502247837340853,0.0765893017418521,0.16097509061073365,24933.540000000008,3.3251187377509073,1350000
29
+ 0.02894687392011301,1000.0,0.0,111.97086033669339,0.822890417632451,-305.1459369610573,-0.009544618815705178,3.3212213405609656,0.21729671797991,0.45082576712876254,0.07020275945735906,0.1538936863503531,24927.08,3.3186101586662113,1400000
30
+ 0.029525773270689018,1000.0,0.0,112.90988224941447,0.7360531060967646,-303.8570275762943,-0.01225661741264148,4.445958421643961,0.22156529916465229,0.464467622305747,0.07311147584686425,0.15613408201605675,24934.08000000001,3.3185172559323206,1450000
31
+ 0.027899613285958698,1000.0,0.0,112.24288835453424,0.7691322883466506,-305.563372260741,0.010997353256046718,3.6336973036491664,0.21311992474764685,0.4356108310332892,0.07430051585147328,0.16231832898832416,24935.24000000001,3.319722179736249,1500000
32
+ 0.025559056798331512,1000.0,0.0,112.4618162902061,0.7791691890873763,-307.136516434935,-0.009810546619072992,3.5932163077581056,0.2049018478393557,0.42319570930809025,0.07140045961695643,0.15928573144629182,24928.64,3.3210179202777717,1550000
33
+ 0.02506244218315923,1000.0,0.0,112.89408913693457,0.7622657191955055,-307.10921194030306,0.0021077650294080244,3.453476492115277,0.20928320694357044,0.43721667131185527,0.0696294337367116,0.15399544680924368,24929.02000000001,3.316370847142277,1600000
34
+ 0.026614732051491757,1000.0,0.0,110.10186222466683,0.7279772125355127,-304.92918868896595,0.02815354127399645,5.8892163143216765,0.20968275983318763,0.43259605310022714,0.07223640852234038,0.15685528274789315,24928.26,3.3271534195858172,1650000
35
+ 0.02479166764754799,1000.0,0.0,112.90559734140764,0.7470417316485211,-304.748418061527,-0.03858435416713281,2.9313564835101524,0.21128850955903564,0.44031472347944606,0.0691642562001911,0.15547535808426582,24931.219999999998,3.319611503011674,1700000
36
+ 0.02563568227972834,1000.0,0.0,112.59384738031093,0.7463635919459032,-305.54516185668996,-0.0011653977148606363,3.815735127017397,0.21297860804200366,0.4461187255910043,0.06827742963934852,0.15453288777220311,24931.82,3.317182546662513,1750000
37
+ 0.025313679638579525,1000.0,0.0,112.25027326296728,0.7791956219653472,-306.0074419561792,0.022147760058492255,3.9881563833463067,0.21177761190712485,0.4458574840262524,0.06731245039831035,0.15376340132733143,24929.700000000004,3.322855465220736,1800000
38
+ 0.025854103856012133,1000.0,0.0,112.99916446981477,0.7240364834976919,-305.76777907653997,-0.0018737531138209558,3.774627640380841,0.21517188126265935,0.4525706260281801,0.06606807623816381,0.1522026349918022,24934.519999999997,3.322846270758786,1850000
39
+ 0.025891420997679198,1000.0,0.0,112.72874632953678,0.7554346636933853,-305.86619889404034,0.01606389166489201,7.5919214540619935,0.21619806696772595,0.44540001106024096,0.08490555328245122,0.1706549439720201,24931.099999999995,3.3197363523244774,1900000
40
+ 0.02580146324433365,1000.0,0.0,111.94559589237754,0.7320805953189555,-305.8906223687774,-0.02010304281733937,4.719982793812781,0.2175162395587567,0.4565199963462389,0.07726924938785606,0.1654532379541209,24932.90000000001,3.3246327658947274,1950000
41
+ 0.024382002054974792,1000.0,0.0,112.53390409034564,0.7672556652350728,-305.1206408557178,0.009577238730043104,3.1056345101785605,0.21714843963205832,0.4642795638301969,0.06594768767684678,0.15117970021768196,24930.379999999997,3.3195125463079718,2000000
42
+ 0.024304374595061,1000.0,0.0,111.82049452037597,0.7353697467575663,-304.033657012942,0.0016472978935391652,4.035076616368289,0.21769534606009458,0.46549490112930625,0.06972390793385821,0.1573482390915626,24928.43999999999,3.318041727679606,2050000
43
+ 0.024013927690088442,985.66,100.37999999999998,111.31422581078361,12.330874310078272,-304.90903459473316,0.007620297397002582,3.308502495002781,0.21158064849823424,0.45323557642132106,0.06981717316589514,0.1594810942813957,24928.32,3.3190425660202374,2100000
44
+ 0.02385312726996825,656.06,283.80415148478716,74.93750406450998,32.817249915444314,-305.9360139032014,-0.014142692703083158,4.107820144294533,0.20987986031532369,0.4506844813439312,0.07416578566107765,0.161937487089386,24930.55999999999,3.3173009626859553,2150000
45
+ 0.02364738754510859,1000.0,0.0,112.15029026174356,0.7402236494494968,-306.30639005737015,0.0011044744833932155,3.2671390517533134,0.21195337610900422,0.45520599959283686,0.06984423124779868,0.1573879205137623,24935.760000000002,3.319583837081306,2200000
46
+ 0.022327092516459552,982.47,122.71002037323603,110.54879124713572,14.952404605378753,-306.36443308105186,-0.005624021188765803,3.410318525356647,0.20907513564184393,0.4484893154445302,0.07218550689391455,0.15647338341745498,24927.98,3.316057535300054,2250000
47
+ 0.02312231081295773,44.85,0.6837397165588672,2.8392714864153312,0.6648761599589187,-305.4416839697215,0.018499668289199085,4.815464965659412,0.20713971136867734,0.43821544825464537,0.07170782126542066,0.15670060420109666,24931.579999999994,3.316495130017148,2300000
48
+ 0.023889723312221577,1000.0,0.0,111.78510946767446,0.740356689153187,-305.239696488035,6.23151189088987e-05,3.7852187942576334,0.21120978953122987,0.45142979608147943,0.07530942387396566,0.16435299001825612,24929.220000000012,3.318448803312121,2350000
49
+ 0.023417908439412313,1000.0,0.0,111.56668162751613,0.742398084045677,-304.9429303948978,-0.007056577989757059,3.5541415730488297,0.21032716361731355,0.4558359896469137,0.07136633697420536,0.15802893900930132,24930.379999999997,3.319332719051842,2400000
50
+ 0.02423599606521442,1000.0,0.0,110.79751734832264,0.7551991507988974,-304.61083031432815,-0.004177426961436944,4.831804704148135,0.21658114852070512,0.45704276125222076,0.0766388505779433,0.16591673722507058,24930.960000000006,3.318067388854425,2450000
51
+ 0.02192129295930263,124.8,0.7615773105863908,10.113472233872594,0.6800572174951758,-305.1273863024928,0.003096395639926293,3.2295519094145435,0.2107827842795835,0.4574179091289625,0.07083762313814393,0.1600492345112774,24930.28,3.3145924414156,2500000
52
+ 0.020842356994748252,1000.0,0.0,111.84813924361067,0.7629092148071265,-306.05806574889993,-0.018701358449161105,2.7717889245712746,0.2093756136980637,0.45529152019888636,0.07059570859785205,0.15932462614917747,24929.82,3.3098109525301522,2550000
53
+ 0.02275675002451999,1000.0,0.0,111.06388432587376,0.757346886673199,-304.765290258791,0.027971635922491595,4.72004260329846,0.21613916296750535,0.46609706761508934,0.07182817518623966,0.16146901356565868,24931.539999999997,3.316047531003907,2600000
54
+ 0.020638851406350436,984.61,107.73002320616106,109.78566145311662,13.078888856292062,-305.00036461303637,0.011072964135780877,2.587550785755495,0.21223527550250684,0.4572698506173472,0.06793182828163555,0.15497914686200082,24930.53999999999,3.3158108048766173,2650000
55
+ 0.020875890520811204,1000.0,0.0,111.96956334462695,0.7483619135878707,-305.1542111010716,-0.013712386674433941,3.252374275337446,0.21655719797432368,0.4713646750828619,0.07303925968959524,0.15996478259459038,24929.08,3.3102080655504764,2700000
56
+ 0.020556497994102686,835.79,310.16683559013853,93.14667324827799,36.60375587881419,-305.7688426153609,-0.016615082846880035,2.341484634459007,0.214468143446445,0.4715104180276404,0.06891577677196248,0.15483352189827765,24932.28,3.314662744773106,2750000
57
+ 0.01897309583149825,1000.0,0.0,111.71575206069188,0.7395891712494729,-305.7182113891665,0.004907441778779761,3.362977973617969,0.2133413695174464,0.4628330266302814,0.07038557337932015,0.156296363367454,24930.159999999996,3.311075300371428,2800000
58
+ 0.019130995753258145,1000.0,0.0,112.18055214793941,0.7357299468030868,-305.07360486266674,-0.011164053843021085,2.4896301135200773,0.2159523766148093,0.48079542484432236,0.06865515196593369,0.15645390510207263,24930.199999999997,3.307680496828392,2850000
59
+ 0.01868577147502509,1000.0,0.0,111.8708689906985,0.7500368827248513,-304.15804157409815,-0.022796264168732077,3.2553889395510924,0.21717118834376298,0.47893120865404304,0.06770574256237641,0.15576598013686063,24931.32,3.31018656483713,2900000
60
+ 0.018421233045756834,1000.0,0.0,112.15472006805723,0.7255734522510718,-304.54300721435277,-0.006545880337133499,2.1630488044142493,0.21152153960183043,0.46999865162313087,0.06696223614082518,0.15465953157533646,24931.539999999997,3.307057516174358,2950000
61
+ 0.011075308073181751,1000.0,0.0,112.03205794872957,0.7486061597329225,-303.48116102843966,-0.11114443928413228,2.279284690747855,0.2190188049042215,0.4849210618639022,0.06747651146173857,0.15693806111423556,24930.640000000003,3.3109041659674263,3000000
hopper_medium_expert_sparse/mobile_based/realnvp/seed_123&timestamp_26-0318-103140/record/consoleout_backup.txt ADDED
The diff for this file is too large to render. See raw diff
 
hopper_medium_expert_sparse/mobile_based/realnvp/seed_123&timestamp_26-0318-103140/record/dynamics_training_progress.csv ADDED
File without changes
hopper_medium_expert_sparse/mobile_based/realnvp/seed_123&timestamp_26-0318-103140/record/hyper_param.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"config": "config_gormpo/hopper_medium_expert_7_realnvp.yaml", "algo_name": "mobile_gormpo", "task": "hopper-medium-expert-v2", "seed": 123, "device": "cuda:7", "dataset_path": "/public/d4rl/sparse_datasets/hopper_medium_expert_sparse_78.pkl", "dynamics_path": "log/hopper-medium-expert-v2/seed_123&timestamp_26-0112-030632/model", "reward_penalty_coef": 0.8, "classifier_model_name": "/public/gormpo/models/hopper_medium_expert_sparse_3/realnvp", "use_wandb": true, "wandb_project": "mobile-gormpo", "wandb_entity": null, "domain": "gym", "actor_lr": 0.0001, "critic_lr": 0.0003, "hidden_dims": [256, 256], "gamma": 0.99, "tau": 0.005, "alpha": 0.2, "auto_alpha": true, "target_entropy": -3.0, "alpha_lr": 0.0001, "deterministic_backup": true, "max_q_backup": false, "norm_reward": false, "num_q_ensemble": 2, "dynamics_lr": 0.001, "dynamics_max_epochs": null, "max_epochs_since_update": 5, "dynamics_hidden_dims": [200, 200, 200, 200], "dynamics_weight_decay": [2.5e-05, 5e-05, 7.5e-05, 7.5e-05, 0.0001], "n_ensemble": 7, "n_elites": 5, "rollout_freq": 1000, "rollout_batch_size": 50000, "rollout_length": 5, "penalty_coef": 1.5, "num_samples": 10, "model_retain_epochs": 5, "real_ratio": 0.05, "load_dynamics_path": null, "epoch": 3000, "step_per_epoch": 1000, "eval_episodes": 100, "batch_size": 256, "lr_scheduler": true, "penalty_type": "tanh", "density_model": "realnvp", "target_dim": 14, "obs_shape": [11], "action_dim": 3.0, "max_action": 1.0, "classifier_type": "realnvp"}
hopper_medium_expert_sparse/mobile_based/realnvp/seed_123&timestamp_26-0318-103140/record/policy_training_progress.csv ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ alpha,eval/episode_length,eval/episode_length_std,eval/normalized_episode_reward,eval/normalized_episode_reward_std,loss/actor,loss/alpha,loss/critic,penalty/lcb_mean,penalty/lcb_std,rollout_info/dynamics_penalty_mean,rollout_info/dynamics_penalty_std,rollout_info/num_transitions,rollout_info/reward_mean,timestep
2
+ 0.26116491563156075,27.87,0.7163099887618488,2.055031186814664,0.6590689554808611,-351.7735037254798,-1.019850341546399,15.838990107917494,0.4470726269684657,0.6202558569680137,0.048084932354214904,0.2098865031542577,249276.58000000005,3.4493763884771953,50000
3
+ 0.1031343172869082,59.98,0.48948953002081663,3.9961423323672585,0.6650975664817691,-528.5371972210685,-0.007233385272883207,22.03491687106592,0.43175318881869407,0.8421366664215947,0.04477906659544738,0.20293428500848534,249321.19999999998,3.4372223509216213,100000
4
+ 0.07654671953119517,107.29,0.7654410493303846,8.762913185849106,0.6828887667356612,-373.0156805645721,-0.017869736302904348,13.897356026132217,0.29669200183331657,0.5173926751807342,0.018830615403756728,0.13391724597273535,249295.78,3.376808366152018,150000
5
+ 0.0626946541534359,68.89,0.661740130262628,4.832673299015524,0.6685831389477903,-317.4374954632617,-0.039655012994221917,6.861380265364678,0.2642368962785646,0.4395014094001066,0.027957127469911684,0.16322940944288494,249318.0,3.3776712092429424,200000
6
+ 0.05128098442472525,67.56,0.6053098380168622,4.890379198746429,0.6625096324277671,-303.26731079590184,-0.033125520244389604,7.524295136325479,0.23185154966771349,0.4193093097004346,0.01952449766985473,0.13661483586003384,249307.74000000005,3.3595519393011806,250000
7
+ 0.039997071658596735,30.95,0.9836157786453001,1.8781389041844871,0.6770551331679477,-301.17152986938675,0.0013675606477260161,8.018637171589138,0.2082342052233232,0.4021893063336621,0.010927320548566174,0.10217186694207116,249314.55999999994,3.344429477024872,300000
8
+ 0.03428560325719432,306.2,155.06579248822095,32.885911851113825,18.548697475782898,-301.7536761920237,-0.04057898127380758,4.844540415296536,0.19447961130022812,0.38168821816458853,0.008831138837894268,0.092763907770716,249328.22,3.336242005447625,350000
9
+ 0.030178122159689624,331.86,35.045690177252894,34.80627323233334,4.73731341150024,-304.9694746105968,-0.010302936170845649,5.947587184894183,0.18301312173053358,0.3735830183745893,0.007962820754785566,0.08783640279180029,249318.18000000008,3.3439015796609057,400000
10
+ 0.031008663238212143,472.9,128.27435441271962,50.64018791413829,15.153067562353645,-304.81922617248426,0.04547748163670232,6.389861958073259,0.18981691933900297,0.38403815435365163,0.006854766805377,0.08195180776870956,249313.94,3.3374494974545215,450000
11
+ 0.028947449640780897,1000.0,0.0,111.82876041004124,0.7592777059554402,-302.7803812646437,-0.006885669404566315,4.967672074960569,0.19597394712761101,0.40101061933935184,0.005892848583748122,0.07599622077792657,249322.03999999995,3.3310563395112234,500000
12
+ 0.0308299951705332,557.19,197.52572971640936,60.18804550257691,23.413261520668634,-301.065344570926,0.017106590144969853,7.080849000344205,0.20557511060878467,0.41878047403394886,0.0056875535324855475,0.07486849015597082,249317.42,3.3349394374229315,550000
13
+ 0.027960801277719254,1000.0,0.0,112.31959210860707,0.8862726326356735,-302.3870615264875,0.003021841049939283,4.339641635233175,0.1937568481790999,0.3938688845139729,0.005354146963978064,0.07262366464663422,249326.26,3.3289800179528797,600000
14
+ 0.025703245173841704,1000.0,0.0,110.82272384530015,0.7845409915312027,-305.7920134051513,-0.021932048973291856,3.7519989977216714,0.1943065156833815,0.4055245906809031,0.005674308179641068,0.07483139976296019,249336.86,3.332444046664222,650000
15
+ 0.025450226946584942,1000.0,0.0,112.7391586653119,0.843262145840147,-305.9820252209469,0.010935929525792882,4.2154080937743545,0.20415329967021872,0.4295260889768632,0.005261630592915357,0.07208852642119494,249323.74,3.3351814184083923,700000
16
+ 0.025811750016249607,1000.0,0.0,111.88234420364367,0.8352765559141679,-306.5175038446025,0.02771169863306009,4.449100406055435,0.20510998380184017,0.4273256765091452,0.004547636312005857,0.06701273329329885,249326.86,3.33408290978494,750000
17
+ 0.026034210177064122,986.01,97.93002552843534,110.71202538366218,11.986956110425814,-306.37151153198204,-0.017064100878760393,3.778006992167235,0.21053953438401096,0.44386317794561375,0.004683580206037843,0.06801874260085392,249325.02000000008,3.3343640995450827,800000
18
+ 0.025261767098344837,40.29,0.9828021163998376,2.496766116944311,0.6886490595736119,-307.0803811969003,-0.010028705833703085,4.186519475785439,0.20457224150359804,0.4306123354607847,0.004776064731913692,0.06858585621251813,249316.28000000003,3.335746939888179,850000
19
+ 0.024497223575040736,1000.0,0.0,112.44366212958093,0.7791500587846165,-307.5506385076895,0.008717742501571767,3.5304884854674285,0.2027728752477464,0.4237349508571633,0.004696406593612193,0.06812051039787913,249315.26000000004,3.335628397653359,900000
20
+ 0.024578248955793698,133.16,20.121987973358895,11.427214031955325,2.973749126061155,-306.9624174298067,0.004357042161300806,3.660298395646757,0.2089198766414832,0.43675980188846014,0.004611996939882728,0.0674513509049853,249326.54000000004,3.3391460960460506,950000
21
+ 0.02482731123119582,1000.0,0.0,112.2058335243524,0.9310761449142391,-307.59831981262334,0.006931475766897168,4.033374404746309,0.20647512249037545,0.4313140897300853,0.005071745126160096,0.07078260359511172,249319.5,3.342386382019961,1000000
22
+ 0.02494518024560041,1000.0,0.0,111.63615755733775,0.7753322796768691,-307.43412825805876,0.008165749509632452,3.952749461278307,0.20661628011837627,0.4322355946674987,0.005029199019964061,0.07044362575715538,249310.61999999997,3.3374606893654155,1050000
23
+ 0.024407309931851993,1000.0,0.0,112.75596504632273,0.7281436966510972,-307.35549427917476,-0.021087312909365014,3.477518035770702,0.2117768996316188,0.4482227708375475,0.005324584503750042,0.07243964495838719,249319.94000000012,3.3366361460226135,1100000
24
+ 0.024553668699041204,1000.0,0.0,112.28868585931092,0.741823837985046,-307.56504655089543,0.011134984881281897,4.259890588005227,0.20985665526479494,0.43837050891220986,0.005208526228979218,0.07155536158458962,249317.41999999998,3.339919656987105,1150000
25
+ 0.022843658978715396,875.82,166.9216810363471,98.31502193628889,20.115244339986095,-308.7715374859605,0.005795077646970839,3.5487814059937266,0.20249630050703973,0.42320379171639444,0.0056668005343691675,0.07476616875805236,249327.97999999998,3.3393273602877374,1200000
26
+ 0.022973159377277143,31.85,0.3840572873934303,1.9976280215050455,0.644210988014572,-309.35712933593055,-0.004369482487104392,3.9403961570847685,0.20523181602581922,0.43414319933742146,0.00526206612977804,0.07198685718119606,249321.90000000005,3.3446451544683704,1250000
27
+ 0.022447346362918626,34.0,0.0,2.135139785438639,0.6282543883756638,-309.23159065613027,-0.00044569292724159235,3.562224804570712,0.20464033971414003,0.4321455573526026,0.005291116002608054,0.07232022131499671,249329.52,3.3388215359742617,1300000
28
+ 0.022591027417592377,990.42,95.31979647481417,111.87964368383523,11.608487935356838,-310.02814295776557,0.011883645893484503,4.273791431262463,0.20244314598396462,0.42219780656069433,0.005163870450067701,0.07130222990405002,249314.46,3.3412176244672995,1350000
29
+ 0.022500094365253718,1000.0,0.0,112.98978046236692,0.8603990232314137,-309.8829400274648,0.055723465955555294,3.6759953042399673,0.2063160595479621,0.4322541678309431,0.005538653735410002,0.07390580637046884,249323.78000000006,3.339491959999776,1400000
30
+ 0.024291705140806585,1000.0,0.0,112.99501849875249,0.7219027173888535,-309.1227954803537,-0.04377062977559879,3.449505550391085,0.21175887983456293,0.4408895089253779,0.005305717146228633,0.07234610947839416,249327.53999999998,3.3421110809407004,1450000
31
+ 0.023353980730846595,1000.0,0.0,112.32039492035723,0.7465843932643799,-309.4446510681101,-0.0012429053033141972,3.4426683536147853,0.20744689678207048,0.43428900728493514,0.0053743677382039,0.07280767490329539,249314.47999999995,3.3423140827946716,1500000
32
+ 0.02280084656998527,1000.0,0.0,112.62807431421476,0.7248354983024644,-308.7076308062803,0.02254244095936455,3.480665728589313,0.2129696765273771,0.44802509479284025,0.004590016686866142,0.06737550263143766,249316.9,3.3390485022953174,1550000
33
+ 0.023065459879673903,1000.0,0.0,112.7135789065016,0.7471390568894414,-308.31258756897125,-0.00595664565287537,3.2270360631978456,0.21344352314770113,0.451228221316041,0.0046442732780901195,0.06775712893582012,249319.79999999993,3.33797113656542,1600000
34
+ 0.023094137561768462,1000.0,0.0,112.53356500583655,0.7368294001969684,-307.3227262982139,0.0026347499155627333,3.5024672143244877,0.2185817223614445,0.4615136350929695,0.0045626826242239835,0.0671729276403436,249324.71999999997,3.334682286475025,1650000
35
+ 0.023114660221822545,1000.0,0.0,112.43220209174373,0.8101874354919313,-306.797325083627,0.006966471554190043,4.215036105716259,0.22068123337954154,0.46739005802750316,0.004865872320572815,0.06931461875691704,249327.24000000002,3.33737561746154,1700000
36
+ 0.022554749870784457,1000.0,0.0,112.78877319247785,0.7166224433317914,-307.073948560783,-0.0043075703506917406,3.5211537407892486,0.22159000594884393,0.4781756957295551,0.004838723562784876,0.06916560528153332,249333.82000000004,3.339266492410124,1750000
37
+ 0.022954944760464138,1000.0,0.0,112.72726724553357,0.7271169366574726,-306.6629586743144,-0.000698462319523059,3.692515347206014,0.22458302064627583,0.47950613391012253,0.004687527786544208,0.0680748223242699,249323.22,3.3345519147768536,1800000
38
+ 0.023083102514632192,1000.0,0.0,112.73528150408842,0.7323219973194848,-306.41745649840834,-0.004365235021039587,3.9898327917815055,0.22404791165471108,0.4759554502964039,0.0045755145019178815,0.06729091516453904,249324.58000000007,3.3370568871354536,1850000
39
+ 0.021739230715855987,1000.0,0.0,112.30892048904724,0.73714089474161,-306.75884464782126,0.004088602670281987,3.213092170202083,0.22356927942678326,0.4827790672343971,0.004609657101265655,0.067533988640202,249326.09999999998,3.3355015287456267,1900000
40
+ 0.022497171883322446,1000.0,0.0,112.29548853819313,0.7147117215479201,-306.0096734783956,0.014150744702443275,4.071256276643231,0.22817566677063417,0.4954886631920923,0.004598865549029048,0.06747916363321979,249335.32000000007,3.3364384967908673,1950000
41
+ 0.022653602744564332,1000.0,0.0,113.05095191983294,0.7365472595553715,-305.7903376269587,-0.006434948590844793,3.435836489248272,0.23158022609353182,0.4976607394948629,0.00476247493174888,0.06867300636104297,249330.26,3.3381332531421366,2000000
42
+ 0.0228092002583669,1000.0,0.0,112.56476683140626,0.7282259114464628,-305.649353909916,-0.003073900167420651,3.8341883342409178,0.23292392411202056,0.5024481741231596,0.004532694298639872,0.06701213556764898,249322.76000000007,3.3363033292537647,2050000
43
+ 0.0225979741047696,1000.0,0.0,112.87732838525142,0.7574538412234753,-306.23719305969166,0.013356927525252206,3.967911031402394,0.22909439536184242,0.4888231333404754,0.004630005225517059,0.06771829914588628,249320.11999999997,3.339091772897454,2100000
44
+ 0.022932372179254944,1000.0,0.0,112.45363838491159,0.7346684985813612,-306.3028361352527,-0.007866345271989667,3.954564447559095,0.22909628080070263,0.48632974898158987,0.004377277003126538,0.06584030427319217,249330.70000000007,3.3370456129844,2150000
45
+ 0.02254814235307298,1000.0,0.0,112.39053658189451,0.7233074560450707,-306.0252953088369,0.0025706293300539864,3.6677358594226916,0.23007158796548766,0.4893918228438548,0.0047292229280016295,0.06844604291474464,249321.2,3.3377391897621123,2200000
46
+ 0.022257318198159053,361.93,319.0356172906091,37.9983192838806,37.9074747337803,-306.74378629943106,0.0014729920127988965,3.3213001726710596,0.22764546516150347,0.4758627523401417,0.004868837922603927,0.06941975485307227,249337.84,3.3382252703574053,2250000
47
+ 0.022674065177216984,1000.0,0.0,112.75642064747386,0.7191387627440516,-306.64438203979654,-0.003886911291331154,3.332022761390205,0.23051260852366617,0.4770286638340376,0.0050399079700644426,0.07060485093739838,249332.38000000003,3.3364734365329904,2300000
48
+ 0.02249698871389021,1000.0,0.0,112.84360484265919,0.7088298592464539,-306.4423375952144,0.005699659713059769,3.418941178834372,0.2314209513169514,0.4799020179256853,0.004755814246717046,0.0686135794317403,249330.17999999993,3.334796031581564,2350000
49
+ 0.022220930929481766,1000.0,0.0,112.79029964948326,0.7241818496876328,-306.5628841979957,-0.005657981961742125,3.1662692091321456,0.2290811315032831,0.46941406985372336,0.004930693215695943,0.06987026246855396,249330.34000000003,3.3358685673941335,2400000
50
+ 0.022060797266848786,1000.0,0.0,112.9861764095293,0.7221322100629148,-307.0763020703111,-0.0005594583535193908,3.1069395602602023,0.22675222561180572,0.46817986748159096,0.004719484896221747,0.06836355960140744,249334.1200000001,3.33475329349677,2450000
51
+ 0.021902318530306036,1000.0,0.0,113.14401157554678,0.736643070909781,-307.3049912225312,0.0013712707103044975,2.9248809301114065,0.2265881620007755,0.4686793449196234,0.004849104227643189,0.06930511531408903,249329.13999999993,3.3346455304061817,2500000
52
+ 0.022512271238528354,1000.0,0.0,112.50821408225504,0.7407116189520748,-306.9294053265464,0.006243536299615945,3.141932015756353,0.23075368394106413,0.4767272433865077,0.004665099133898021,0.06798897038836141,249336.86,3.3356864266160295,2550000
53
+ 0.022474054044224322,1000.0,0.0,112.86447552731673,0.712707002770552,-305.7030963092026,-0.003294863781780042,3.300276371322888,0.23730010418921904,0.49378610052078714,0.004730190264376271,0.06844645656266986,249335.0199999999,3.3354431418107047,2600000
54
+ 0.021383834217860796,1000.0,0.0,112.8832832440991,0.7167799056260397,-305.95929082092476,-0.0029721823003142963,3.074272138875756,0.2332688833332075,0.4872240484690653,0.004409858971837782,0.06609441820634224,249340.84,3.3314037267540013,2650000
55
+ 0.022028392546065135,1000.0,0.0,112.8503380097416,0.7311665635916877,-304.9282442413289,-0.004443028674870731,3.539405703761566,0.24001013211190636,0.5051901418244858,0.00435624123969462,0.0657012231279444,249334.86,3.3323894008138515,2700000
56
+ 0.021808086410946767,1000.0,0.0,113.0442132475717,0.7226864634675753,-304.0172726544153,0.0077763767896591625,3.669752186156517,0.24005112877667062,0.5067747134482844,0.004407269861686036,0.06608883604278114,249329.08000000007,3.332702629445428,2750000
57
+ 0.02161312621358782,1000.0,0.0,112.9931410584198,0.7280793870220204,-304.3180195910646,-0.004425582589954148,2.999578442212363,0.23287360092937834,0.48539934964299053,0.004302242866919667,0.0653094494676726,249320.08000000002,3.330729654641533,2800000
58
+ 0.022347066443525243,1000.0,0.0,112.71284998447759,0.7256280702207998,-303.99039512267234,0.011671110606528892,3.663809194397959,0.24024528219998056,0.50389773017495,0.004384252421256955,0.06592486060185095,249334.81999999998,3.3345821282488117,2850000
59
+ 0.020929551769792606,1000.0,0.0,112.88267648953992,0.7153434559479507,-303.55255142516654,-0.028276828511133906,3.116148198609413,0.2361677482816571,0.4926981906932588,0.004166742632141319,0.06426998972246864,249331.02,3.3319722526599977,2900000
60
+ 0.02166654678683736,1000.0,0.0,112.91010769242624,0.7069423538543238,-303.02965474975053,0.013681830302626543,3.541376750198606,0.2406342767348868,0.5048093780455032,0.004207740873688453,0.0645844614450303,249330.2,3.3341388535842187,2950000
61
+ 0.02194972433272749,1000.0,0.0,112.89523398700454,0.727496785566162,-302.13197693359024,0.005754661229923446,3.3000747009587403,0.2449111460816874,0.5161323860868836,0.004224472396797003,0.06471738741849575,249325.80000000002,3.329830055063758,3000000
hopper_medium_expert_sparse/mobile_based/realnvp/seed_42&timestamp_26-0317-002436/record/consoleout_backup.txt ADDED
The diff for this file is too large to render. See raw diff
 
hopper_medium_expert_sparse/mobile_based/realnvp/seed_42&timestamp_26-0317-002436/record/dynamics_training_progress.csv ADDED
File without changes
hopper_medium_expert_sparse/mobile_based/realnvp/seed_42&timestamp_26-0317-002436/record/hyper_param.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"config": "config_gormpo/hopper_medium_expert_7_realnvp.yaml", "algo_name": "mobile_gormpo", "task": "hopper-medium-expert-v2", "seed": 42, "device": "cuda:7", "dataset_path": "/public/d4rl/sparse_datasets/hopper_medium_expert_sparse_78.pkl", "dynamics_path": "log/hopper-medium-expert-v2/seed_42&timestamp_26-0112-030627/model", "reward_penalty_coef": 0.8, "classifier_model_name": "/public/gormpo/models/hopper_medium_expert_sparse_3/realnvp", "use_wandb": true, "wandb_project": "mobile-gormpo", "wandb_entity": null, "domain": "gym", "actor_lr": 0.0001, "critic_lr": 0.0003, "hidden_dims": [256, 256], "gamma": 0.99, "tau": 0.005, "alpha": 0.2, "auto_alpha": true, "target_entropy": -3.0, "alpha_lr": 0.0001, "deterministic_backup": true, "max_q_backup": false, "norm_reward": false, "num_q_ensemble": 2, "dynamics_lr": 0.001, "dynamics_max_epochs": null, "max_epochs_since_update": 5, "dynamics_hidden_dims": [200, 200, 200, 200], "dynamics_weight_decay": [2.5e-05, 5e-05, 7.5e-05, 7.5e-05, 0.0001], "n_ensemble": 7, "n_elites": 5, "rollout_freq": 1000, "rollout_batch_size": 50000, "rollout_length": 5, "penalty_coef": 1.5, "num_samples": 10, "model_retain_epochs": 5, "real_ratio": 0.05, "load_dynamics_path": null, "epoch": 3000, "step_per_epoch": 1000, "eval_episodes": 100, "batch_size": 256, "lr_scheduler": true, "penalty_type": "tanh", "density_model": "realnvp", "target_dim": 14, "obs_shape": [11], "action_dim": 3.0, "max_action": 1.0, "classifier_type": "realnvp"}
hopper_medium_expert_sparse/mobile_based/realnvp/seed_42&timestamp_26-0317-002436/record/policy_training_progress.csv ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ alpha,eval/episode_length,eval/episode_length_std,eval/normalized_episode_reward,eval/normalized_episode_reward_std,loss/actor,loss/alpha,loss/critic,penalty/lcb_mean,penalty/lcb_std,rollout_info/dynamics_penalty_mean,rollout_info/dynamics_penalty_std,rollout_info/num_transitions,rollout_info/reward_mean,timestep
2
+ 0.2365185591632097,65.32,0.8471127433818948,4.51883934117017,0.6815795316492415,-304.0288671909814,-1.2821332891710568,11.839841928591081,0.3731706512622897,0.5734940552181941,0.03333010297038266,0.17583148314888544,249289.7,3.4653253748279345,50000
3
+ 0.08756909837275828,45.84,0.9666436778875658,2.999102800077246,0.6699929149365633,-460.28600704346,-0.01264750612847498,16.790365831909433,0.3850476263186383,0.8310552110698916,0.028467938654989762,0.1647415640486415,249321.05999999997,3.481535092874976,100000
4
+ 0.0683879406208539,57.52,0.8997777503361595,3.962143885407014,0.686747467808566,-366.6664687207027,-0.05530815231200254,11.157183255071551,0.2602400791937064,0.47524155284404973,0.017152452095635432,0.12790614247709442,249315.4,3.401904057806964,150000
5
+ 0.04557593183651548,63.52,8.111078843162604,4.527905868290056,1.3230646229980092,-326.90442191467724,-0.026381885193735077,8.70072909894359,0.20344967218816198,0.3712978700190769,0.012989904986034771,0.1115640631648054,249318.13999999998,3.390162086301206,200000
6
+ 0.03844699276551528,98.84,0.9457272334029511,7.516784453890954,0.7099126933547306,-320.6089158050596,-0.012033361204825893,6.578411324719132,0.18172733623847329,0.35168574887991255,0.007384432591740095,0.08506024685833251,249318.81999999992,3.353283328990806,250000
7
+ 0.03709062861025243,415.32,44.75307363746093,44.91281065958233,5.9190409943158135,-318.423697008664,-0.0105900154557821,7.692545542199508,0.17953151034146506,0.34039286143348235,0.006716098731256459,0.08028060889589617,249325.85999999996,3.349838731164286,300000
8
+ 0.031075200392938925,398.57,28.10916398614516,42.259901769600525,4.1505819909087425,-317.37437504333514,-0.008408755569904707,5.281940455291248,0.17196000425636757,0.34118946906328235,0.005974527616200939,0.07627745487175243,249318.37999999998,3.3393484104334896,350000
9
+ 0.029031107450947218,36.53,1.062591172558854,2.341798142661576,0.6882552935797499,-316.5543550671359,0.020970848017111816,6.556429923847906,0.17397076870351724,0.3623932598067813,0.006503156721211859,0.07979711487591867,249333.15999999995,3.3385521614159566,400000
10
+ 0.027509196121468852,344.93,21.567686477691574,36.593512116172796,3.6409245600600144,-315.81033077026245,0.003702131205648052,5.29947038398742,0.16959590977221778,0.35985821439102206,0.005653897932088453,0.07470557214941664,249334.02,3.326920789284276,450000
11
+ 0.028015511788241566,65.18,90.35202045333574,5.388745221528616,10.73860481331858,-313.8205511401352,0.014290720847993887,5.192471283477579,0.17623361419290118,0.3612947439040187,0.005987987736668849,0.07681291828567785,249328.66,3.3365266668550486,500000
12
+ 0.02813840013921273,234.64,0.7939773296511684,22.825080960435447,0.7150953443690927,-313.64430092833936,0.006392022399380843,5.784658835808694,0.17602276408359085,0.3700794601421078,0.005853446779144749,0.07577947160361753,249319.88000000006,3.331578361517195,550000
13
+ 0.028462236652560532,186.57,4.32031248869801,17.567689073817284,1.262651870656599,-312.71251066467465,0.007414731866344896,4.386177046161196,0.177696160878094,0.3679907866758148,0.0057395735641304875,0.07516374201995596,249320.04000000004,3.3304328496803954,600000
14
+ 0.027532911726609082,217.4,2.86705423736629,20.799984365347363,0.9447946446947183,-313.7357583666949,-0.015000912167914169,4.17068648369371,0.17914372293964237,0.37480925888747124,0.0061498831968741586,0.07775827956583527,249327.73999999996,3.3247535584530628,650000
15
+ 0.02763802532643084,438.92,153.69487174268372,47.58896883684217,18.99896247005403,-311.8555598516887,0.02322495617903797,3.984200806503345,0.19015683923483132,0.3801476130515306,0.006351397501725325,0.07882597098949012,249336.5,3.3282479919879524,700000
16
+ 0.02948001807793963,322.25,38.432635871092685,36.0013778599194,5.67968801331994,-309.1717721234166,0.01328353966038696,5.395449716458349,0.19939906667277452,0.38754988685310027,0.005782318036969151,0.07535854869572349,249328.2000000001,3.3396805710473414,750000
17
+ 0.02990220823857934,109.3,1.5264337522473748,8.473617099912333,0.7616170485537931,-307.98087101745995,-0.018632950980663324,4.521323755155871,0.20230545213729112,0.39058404510587663,0.005213532135577631,0.07167211833988059,249331.19999999998,3.3384388075346694,800000
18
+ 0.027559412585720165,124.03,0.7273926037567333,10.071475321784416,0.6788970418941382,-308.5647408203188,-0.0067309750779716,4.872127937474282,0.2013735048222503,0.3998260014136124,0.005426260899064207,0.07320468911192332,249327.6799999999,3.3340636698994444,850000
19
+ 0.02774373551100495,1000.0,0.0,109.83441465812606,0.9418190881227652,-308.5252663488785,0.014749070806316492,4.256667130166286,0.20961302940875343,0.4108603669312636,0.005386227058535561,0.07294360238433353,249338.08,3.3394947448440555,900000
20
+ 0.028337007186040458,1000.0,0.0,110.27080282792589,0.8834741190477134,-307.5069715832542,0.002297211986481723,4.24734203537938,0.20921171289116158,0.40481596622779775,0.0050270147898319505,0.07043394934731009,249330.2400000001,3.343191087362998,950000
21
+ 0.028898353747278647,130.38,1.084250893474384,11.069616915851006,0.7564545400647738,-307.22697391663144,-0.007349375456199202,4.567805859748196,0.2153913569313298,0.43155958084076473,0.0051793764679682235,0.07151550647717711,249318.46,3.3408880018317726,1000000
22
+ 0.02856407153915645,1000.0,0.0,111.30370809968797,0.817347934375074,-308.0252880114757,0.020198136942908236,5.6073417543362805,0.20947194134771843,0.419469500332181,0.005078696116733388,0.07073903930585808,249321.02000000008,3.338551094778076,1050000
23
+ 0.027796582944207143,308.68,184.36159469911297,32.09802113692971,22.105187185184942,-307.60639884094667,-0.0225802103617787,3.8457600574516944,0.21592982545882286,0.4335758658903832,0.005507532375689062,0.07367097951499786,249325.44,3.3431950608604404,1100000
24
+ 0.027302650668472078,1000.0,0.0,111.85102670326063,0.8018443051982618,-308.49965787841563,0.010074913964047904,3.9660429664099492,0.21308007710814544,0.4299269885911069,0.005320287541268879,0.07245896781666222,249340.06,3.343807594137508,1150000
25
+ 0.02751530869290209,927.51,143.32030526062942,104.77912254058405,16.780383287525012,-308.65345208862317,-0.0058879316759854975,3.382660333075522,0.21463425121516094,0.43725404428779796,0.005462766008815836,0.07347448388311736,249336.47999999998,3.3399299253742742,1200000
26
+ 0.027208874580636384,24.1,0.29999999999999993,1.5571587461230467,0.6377693162492615,-308.0142124749714,0.0014971922304483315,3.5558980421865045,0.2124379543003512,0.4318605145630268,0.005788580872322374,0.07564294332628956,249324.46,3.3377071151957325,1250000
27
+ 0.025944465922676362,1000.0,0.0,111.71526531641645,0.8267182415391525,-309.1375094885226,-0.007008904928714158,4.163307301617868,0.20341343820273608,0.4201015382960455,0.00566036217140221,0.07470339200383136,249337.48000000004,3.3355795649376483,1300000
28
+ 0.025082050596959955,1000.0,0.0,107.72264435834296,1.29715256165168,-309.82511797668064,-0.0021117040805145853,3.406424804228535,0.20257742298841644,0.4205241474714864,0.005234873616370764,0.07190073850491689,249333.42000000007,3.3326302859786603,1350000
29
+ 0.024524670620038987,1000.0,0.0,112.25383394436474,1.0256478019989146,-311.47890341430593,0.0008203130091728317,3.994394064641712,0.19567067863941015,0.4045355256575374,0.005336552069348561,0.07255505979054594,249330.62000000005,3.334563679434537,1400000
30
+ 0.02411370101839292,978.63,91.62539549710003,111.41846737605358,11.024996149541986,-311.79024879150677,-0.008092343440130515,3.6040236898577005,0.1972688926467285,0.4092487786027812,0.005109253305402808,0.07096957769824006,249332.3,3.3347324642708513,1450000
31
+ 0.023678132049329545,1000.0,0.0,111.43138542541584,0.8175206562952538,-312.2215442669672,0.017336273347735378,3.0218110463666776,0.19799977012977113,0.41246528069823324,0.005018148532874988,0.07043717750367777,249333.9,3.330673256616255,1500000
32
+ 0.024124951251707466,1000.0,0.0,112.74134760879792,0.8521811822163005,-311.9539277862543,-0.009079168528318545,4.240064225211177,0.19815823257088505,0.41423632053166715,0.004898124559183121,0.06955682163929627,249338.78000000003,3.3346707277710754,1550000
33
+ 0.023250251520611546,1000.0,0.0,113.03595473556469,1.0819005030739526,-312.7941285345439,-0.005829777652174141,3.0378672070205246,0.19469750371142822,0.41027966870903526,0.0044940212405995454,0.06653983838411004,249340.50000000003,3.3357358451479335,1600000
34
+ 0.022604970587044984,1000.0,0.0,112.43875498070055,1.1232017340473703,-313.2561861114538,0.0024707174684107866,2.766086737584502,0.19643270318671824,0.40933109926506944,0.0040723909902811205,0.06337436604246348,249334.86000000004,3.330560517771486,1650000
35
+ 0.022194877189882042,1000.0,0.0,113.32293485175879,1.2811848970112134,-313.7617411004594,0.007362751676477403,3.117134244059308,0.19479445507958465,0.40255266418322566,0.004213719597018485,0.06445667736698962,249341.53999999998,3.3345731714807743,1700000
36
+ 0.02164454680126187,702.16,303.18475291478626,79.7649550136815,35.99444486992171,-313.8223705535879,-0.020897459909767362,2.639655544459835,0.1921727438934157,0.4018880945181849,0.004377805599701118,0.0657956234224817,249337.68,3.335539225582145,1750000
37
+ 0.022452696680352015,1000.0,0.0,112.65754312287808,0.9264292037559602,-313.86370239502526,0.004926490566506794,3.4206317228841723,0.1915804538330433,0.40092064747139683,0.004342534649224523,0.06546087601777524,249341.82,3.3367691202230656,1800000
38
+ 0.0211825458466634,1000.0,0.0,113.41902902039709,0.9942667691415055,-314.3933523455833,0.00747760742116711,2.503489976719691,0.18957130020513965,0.3967799427671738,0.004122339184772308,0.06381358964060209,249327.96,3.331851147835434,1850000
39
+ 0.022427231719232964,520.58,202.58164675014368,59.64420187100812,24.666313102979377,-314.01086910766196,0.013581970088481917,3.0708508910149166,0.1979851190726466,0.4156655180650955,0.004073948396210758,0.06347976590238015,249339.80000000013,3.3336704975899245,1900000
40
+ 0.0221465053709225,1000.0,0.0,112.82117689241862,0.7874300681406604,-314.13236705261414,-0.010585877201408087,2.652421146869696,0.19673228791490233,0.4138030159623947,0.004113224087657813,0.06379809989861149,249343.66000000003,3.330693961892688,1950000
41
+ 0.02239811458740397,1000.0,0.0,112.33812448675589,0.7769881664434266,-313.71671649596794,0.023749754286035995,3.6112591136991945,0.20005560739516887,0.4224398395329743,0.004276696395979142,0.06505366389379835,249333.46000000008,3.3326668924930956,2000000
42
+ 0.022206149619818302,947.11,149.74016795769933,107.15790680852453,17.1366917603159,-313.34337422912955,-0.023542368194535816,2.8981083344972536,0.19834158829063142,0.424548128289727,0.0041115716726924,0.06376128031307658,249337.98000000004,3.329261017404835,2050000
43
+ 0.021670404730811783,915.47,253.59004140541484,103.0153908801342,30.338921033660544,-313.94114195251143,0.002547005114927803,3.0947007435864133,0.19478496095404163,0.41075183009848126,0.004112388582705635,0.06372768099170872,249326.43999999992,3.329540088092856,2100000
44
+ 0.021553250524774237,208.7,183.54686050161686,20.53821007335121,22.683816709402656,-313.87925493285917,0.00030350273363287226,2.6721810538137483,0.1963631310103843,0.4158148097735677,0.004092011170142948,0.0636465718230045,249333.02,3.3300976215482296,2150000
45
+ 0.021641716681160023,952.89,121.49460029153559,109.08034251214454,14.304173154166516,-313.94838767273467,0.00035953020386382534,2.766211275196095,0.19559784497767796,0.4132303647485379,0.003982481408678644,0.06279989176623249,249342.39999999997,3.331814457556815,2200000
46
+ 0.020869045118838605,341.29,350.3349338847041,35.62860439906247,41.67706729294073,-313.8502372076457,-0.0008697363861650321,2.9396273640489885,0.19669226869806744,0.4183244725581942,0.00427387073412975,0.06501873601697572,249335.77999999994,3.331548890114895,2250000
47
+ 0.021117548098713308,212.4,201.07874079573904,20.258704948920066,24.655064113050113,-313.37359928284167,-0.005718297149836923,3.441357994147522,0.19603017877683176,0.41523238879592,0.0037515758993265807,0.0609478794498624,249330.8200000001,3.3334212957753833,2300000
48
+ 0.02079800043877281,1000.0,0.0,113.06377788784552,1.1501772199604767,-313.6516884613075,0.01978567558325843,2.5951312211757975,0.19720936016589258,0.42109479324578575,0.0036177733216290198,0.05987367929716529,249323.07999999996,3.329776048534731,2350000
49
+ 0.020755923953615293,1000.0,0.0,112.7752437967295,0.8108430199914309,-314.235157022098,-0.02067280900984941,2.5499506766974886,0.1960611703333273,0.4168767714679226,0.0037312950700498296,0.06079499905494598,249326.62000000005,3.331656747520157,2400000
50
+ 0.020998854292109525,1000.0,0.0,113.40310000985528,0.9540043227489278,-314.517347572631,0.009684978437460825,2.551343741710189,0.19764431387185916,0.4179391561813668,0.0037647289955265416,0.061082553712768405,249334.99999999994,3.3262314929824224,2450000
51
+ 0.02138213361982228,797.38,256.20408974097194,90.99932596296972,29.584619477890488,-314.16580319518215,-0.006106808714791837,3.3289166239815446,0.19757158519014803,0.4184162491896739,0.0038961812834087868,0.062147432458300504,249331.98000000007,3.3281060044325685,2500000
52
+ 0.02069949341244947,922.05,170.72547408046643,105.9498358434265,19.517406240654502,-314.7018608245834,0.00514062023177751,2.569096328129196,0.19570503631368127,0.4165176494029135,0.0036573451471610574,0.06021131240238575,249338.12000000002,3.329187981777769,2550000
53
+ 0.02075953038092687,1000.0,0.0,113.0281499405552,0.9491097602596674,-314.5352221844488,-0.0008142751950771172,2.508385040104348,0.19820436764001645,0.41964653932437584,0.0038196146746937677,0.06151051643997657,249342.64000000004,3.3308210621106964,2600000
54
+ 0.020772168382480524,1000.0,0.0,112.57193078383747,0.9356161528406747,-314.2740180657946,-0.006200044817477491,2.5333754633515615,0.20041987408369585,0.4238946370194879,0.003965158997534561,0.06268859294997241,249336.15999999995,3.327454006029179,2650000
55
+ 0.02103981018289899,1000.0,0.0,112.90700886234892,0.9910369238710283,-313.95953675782147,0.002785392773598219,2.6992670163440686,0.20092959892123785,0.42084857541054393,0.0037224737583707174,0.0607416640179821,249330.94000000003,3.3294452114335518,2700000
56
+ 0.020355019660927728,1000.0,0.0,112.57983186808151,0.8143775608085999,-313.91986428649267,-0.021113757267146906,2.6777424884652956,0.2021349953326581,0.4295006029964972,0.0037660110109115066,0.06109745310129491,249326.29999999996,3.3306266515279197,2750000
57
+ 0.020255031993128114,1000.0,0.0,112.35882584405029,0.8341110490554214,-313.96670692077555,0.02140845185153199,2.3862801354581866,0.202919285601975,0.4289668524017937,0.0037496700076320817,0.060978591414397855,249345.6200000001,3.32799625340645,2800000
58
+ 0.020069634260088214,1000.0,0.0,112.6571194170607,0.9199685367797177,-313.9620865692185,-0.00370211910992903,2.2753939979720372,0.2020642789901784,0.42794337086438944,0.0035972825870223585,0.05972828250629413,249336.29999999996,3.3291260176782176,2850000
59
+ 0.01957452460173509,1000.0,0.0,112.78319666658925,1.0886684068490713,-313.7468060986294,-0.014577390736937576,2.449807993047845,0.20290034214496608,0.43574107998728456,0.0038089854734313544,0.061461700773920096,249329.5400000001,3.3275063279708665,2900000
60
+ 0.019108255428485897,1000.0,0.0,112.59693354298126,0.9164934490915313,-313.5882205584705,-0.026062755161151276,2.362498355419062,0.2039544465862227,0.43193228957519175,0.003791419686832431,0.06131427624940736,249337.46,3.331081186261495,2950000
61
+ 0.021206942459456604,1000.0,0.0,112.53336352318108,0.8747791219994092,-313.31366747558405,0.08669307907037464,2.2360401734912494,0.20546854186937216,0.43250090871662095,0.003737310285745613,0.060889077846739706,249344.91999999998,3.331704437665962,3000000
hopper_medium_expert_sparse/mobile_based/realnvp/seed_456&timestamp_26-0319-223848/record/consoleout_backup.txt ADDED
The diff for this file is too large to render. See raw diff
 
hopper_medium_expert_sparse/mobile_based/realnvp/seed_456&timestamp_26-0319-223848/record/dynamics_training_progress.csv ADDED
File without changes
hopper_medium_expert_sparse/mobile_based/realnvp/seed_456&timestamp_26-0319-223848/record/hyper_param.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"config": "config_gormpo/hopper_medium_expert_7_realnvp.yaml", "algo_name": "mobile_gormpo", "task": "hopper-medium-expert-v2", "seed": 456, "device": "cuda:7", "dataset_path": "/public/d4rl/sparse_datasets/hopper_medium_expert_sparse_78.pkl", "dynamics_path": "log/hopper-medium-expert-v2/seed_456&timestamp_26-0112-030630/model", "reward_penalty_coef": 0.8, "classifier_model_name": "/public/gormpo/models/hopper_medium_expert_sparse_3/realnvp", "use_wandb": true, "wandb_project": "mobile-gormpo", "wandb_entity": null, "domain": "gym", "actor_lr": 0.0001, "critic_lr": 0.0003, "hidden_dims": [256, 256], "gamma": 0.99, "tau": 0.005, "alpha": 0.2, "auto_alpha": true, "target_entropy": -3.0, "alpha_lr": 0.0001, "deterministic_backup": true, "max_q_backup": false, "norm_reward": false, "num_q_ensemble": 2, "dynamics_lr": 0.001, "dynamics_max_epochs": null, "max_epochs_since_update": 5, "dynamics_hidden_dims": [200, 200, 200, 200], "dynamics_weight_decay": [2.5e-05, 5e-05, 7.5e-05, 7.5e-05, 0.0001], "n_ensemble": 7, "n_elites": 5, "rollout_freq": 1000, "rollout_batch_size": 50000, "rollout_length": 5, "penalty_coef": 1.5, "num_samples": 10, "model_retain_epochs": 5, "real_ratio": 0.05, "load_dynamics_path": null, "epoch": 3000, "step_per_epoch": 1000, "eval_episodes": 100, "batch_size": 256, "lr_scheduler": true, "penalty_type": "tanh", "density_model": "realnvp", "target_dim": 14, "obs_shape": [11], "action_dim": 3.0, "max_action": 1.0, "classifier_type": "realnvp"}
hopper_medium_expert_sparse/mobile_based/realnvp/seed_456&timestamp_26-0319-223848/record/policy_training_progress.csv ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ alpha,eval/episode_length,eval/episode_length_std,eval/normalized_episode_reward,eval/normalized_episode_reward_std,loss/actor,loss/alpha,loss/critic,penalty/lcb_mean,penalty/lcb_std,rollout_info/dynamics_penalty_mean,rollout_info/dynamics_penalty_std,rollout_info/num_transitions,rollout_info/reward_mean,timestep
2
+ 0.23589090233236093,67.09,0.6015812497078014,4.727622355479362,0.6618500483252912,-318.3240748878996,-1.047820079908435,12.975309820692274,0.39187142445524437,0.5538114171186025,0.04508774037567283,0.20203714221211597,249251.65999999997,3.4404815206218218,50000
3
+ 0.07697842760220079,63.15,0.4330127018922193,4.38683402125193,0.6579309731522571,-416.81661662719523,-0.01303670814830826,14.84058692400226,0.3381336828622168,0.6077008309933503,0.03338945848190784,0.17678745343722865,249320.80000000008,3.4104678216911486,100000
4
+ 0.062156794905885944,38.63,3.3456090626371755,2.4645960632634587,0.8472100156508986,-352.33919424926927,-0.03570113142065652,8.819722048378022,0.2519212382444776,0.4330565152981899,0.013410227749622678,0.11336905011149276,249311.34,3.364453162365629,150000
5
+ 0.04314586168326393,281.4,6.848357467305573,29.53634677980153,1.482178573518008,-314.67191222534416,-0.02618448558643472,6.646396549223748,0.18711270338937555,0.348527492070645,0.005621043514320548,0.07430794939147305,249316.72000000006,3.3582337801704134,200000
6
+ 0.03682083007395272,620.95,153.37153419067047,69.49098465222418,18.616439867895384,-308.91618546326345,-0.03389450461611093,5.93299503136388,0.17314385857328968,0.3363190764276716,0.005436685459805393,0.07301792538247845,249318.43999999992,3.3553817446752108,250000
7
+ 0.031185098229869777,125.91,2.408713349487647,9.618537302852461,0.8455541219753393,-309.01451627441776,-0.00906965308077637,5.337064344750678,0.17290430097967602,0.3477588224315605,0.005357253312764694,0.07259354451676577,249326.13999999998,3.3366398359223957,300000
8
+ 0.031168741256631917,425.56,93.3887916186948,45.6453114228359,11.906522478843236,-308.9888681579563,0.014159684470518975,5.752823508629741,0.17543309958174919,0.3512410232673589,0.0056803190700943276,0.07466105272206493,249311.20000000007,3.3387242983709196,350000
9
+ 0.030352456773743233,316.98,19.412356889363018,32.557923293577474,3.1781863906670322,-308.89088174255824,0.0003475568446517179,5.506354007914151,0.17848114815876065,0.35624570985227966,0.005256153293976455,0.07203962043569814,249322.58,3.335638607270819,400000
10
+ 0.031802636574395644,171.69,92.81720691768311,16.544129812077582,10.042550254845729,-304.46452283508467,0.015229752976745205,5.46500794244644,0.1976575788454683,0.3816287468522768,0.0050137432742428075,0.070280479374694,249319.69999999995,3.3441224520396835,450000
11
+ 0.030460970225743896,1000.0,0.0,109.46556231788232,0.7973517233095905,-303.7013441339154,-0.02682535691626369,6.710318696033934,0.19890549654021764,0.38447560150131266,0.005394201570337071,0.0729155018420552,249323.02,3.343201332872964,500000
12
+ 0.02790089944861832,913.79,172.27874477137337,96.83300130562775,19.71642488383067,-305.3001282849126,0.004295519721582549,5.959234191154236,0.1936335226769759,0.38743240158155356,0.005240670803583206,0.0719755934574417,249304.84000000003,3.3306900709378935,550000
13
+ 0.027578322667665873,1000.0,0.0,109.02980171582051,0.9079811668573156,-306.90600520934987,-0.006409579076841577,5.149892052655099,0.19301037919566222,0.38384098877221506,0.004842036191820519,0.06919022868173146,249321.18,3.3335548946119813,600000
14
+ 0.02660482172746219,392.26,129.34826013518696,42.0458712638834,15.812826129367613,-307.48673461791464,0.057634761861488214,5.776223775490496,0.18708995872080408,0.3706930444554948,0.004845949834414844,0.06923538271110354,249307.52,3.332758531149447,650000
15
+ 0.027797640229501062,297.03,1.1353853971229328,29.465349196455936,0.7746359794024674,-310.00603046936106,-0.026174954139218637,5.464452586439262,0.18895943724661945,0.3817314204788211,0.005209209644912257,0.07172838851013988,249314.44,3.324160963649857,700000
16
+ 0.027372145995572063,128.88,0.7110555533852472,10.42571447494203,0.6735534418596574,-310.57907179016354,-0.008582643783912014,3.5393982301711917,0.19264376029386954,0.3901460162368418,0.005217240371103098,0.07184700849298804,249307.28000000006,3.3221209729795964,750000
17
+ 0.026680499463603145,50.13,0.6108191221630179,3.1977991449976546,0.6629203214519821,-309.7625205407713,0.006241616173088699,4.21288581758258,0.19445451327800695,0.3934736681804114,0.005027476422526334,0.07046940387632082,249310.89999999997,3.3259184620571736,800000
18
+ 0.026270507899820755,123.38,9.104702081891533,9.79581976461156,1.40438970617748,-310.3834252148406,-0.014529953795373326,3.9371763084423073,0.18694369640112385,0.38144667827456763,0.005034768261641983,0.07055744638985981,249314.22,3.3290105932041647,850000
19
+ 0.024506577132977624,19.61,0.4877499359302879,1.3277199492295304,0.6437251146294437,-310.720136567992,0.022253866123706008,3.608288125020249,0.1881395317871851,0.3837388696773372,0.004760428683726212,0.06859708813437833,249310.85999999996,3.3283779628458636,900000
20
+ 0.024813828511126203,234.81,282.5811633849645,22.864098352047794,33.071775954834045,-311.29843342774024,0.011476207011640129,4.340478400252455,0.1870186639153954,0.37985420216709986,0.004579805243076699,0.06728325956194497,249311.61999999994,3.3315789680780674,950000
21
+ 0.023871875755861336,430.91,80.96605399795645,48.35654311969839,10.14325301505486,-311.3123765319827,-0.011436679350212078,3.21137645498515,0.1904054779243483,0.38865135654867283,0.005117414237515952,0.07112609209737959,249303.5,3.338423958304242,1000000
22
+ 0.024045663727149336,124.57,0.9823950325607311,10.151719377525781,0.7055142003737338,-311.5215881982358,-0.017112882039100122,3.3751361983925015,0.19265469203472255,0.39230419703722197,0.005001096306625389,0.07031826129688115,249317.15999999992,3.3396237268090476,1050000
23
+ 0.02380751464452602,131.04,87.33829858658801,11.098869378301456,10.812188042897242,-311.24218028808747,0.025759262542799536,3.6912733243614295,0.19425174866393496,0.39635043753251503,0.004590539816865908,0.06735301035006165,249323.71999999994,3.340323100831086,1100000
24
+ 0.02339533952653387,190.57,212.51791712700367,17.927701754303342,25.749097419874005,-312.6094831024214,-0.002079467402026049,3.048567183827126,0.18999370681539265,0.3867397776138788,0.00424893583982249,0.06466808431274215,249326.03999999998,3.345885433051024,1150000
25
+ 0.02283631283000083,1000.0,0.0,112.09699592853934,0.7781094093200177,-313.0158713555868,-0.01276981038928028,3.2044097490000483,0.18578020453885263,0.3837838906575744,0.004310572638591445,0.06521771684282635,249331.28000000003,3.343787559729948,1200000
26
+ 0.022686917226426323,200.86,0.8368990381163071,18.426007986636503,0.6921279405428148,-312.3288341570978,0.014409387115240408,3.7420519066261946,0.18645108082472997,0.380824138475958,0.004372974133444663,0.06572009779445101,249317.76,3.335349108680319,1250000
27
+ 0.023198683003298862,1000.0,0.0,112.3174002599042,0.9524060617928807,-312.70915363464457,0.013287003998681985,3.4573143659811856,0.1884483013480869,0.3947769262412177,0.004300503148416685,0.0651534124458509,249318.86000000004,3.3353191634153783,1300000
28
+ 0.022761268696188684,967.98,133.5973787167997,108.6791197372788,16.149863089370335,-312.4785208544927,-0.0026551198036222695,2.750229978266352,0.1887598504836839,0.39280563670397667,0.004040803677329931,0.06322434428883146,249318.7,3.3327541673370615,1350000
29
+ 0.02344839511591975,761.76,228.73207558189122,85.52270046661535,27.5256033325343,-310.9052781762657,0.01261089042797744,4.154362266157353,0.19535361252322705,0.4049682477885479,0.004104473367638361,0.06367951325002563,249323.13999999996,3.3362034300963037,1400000
30
+ 0.023177733011543515,1000.0,0.0,111.79667348806161,0.738826926010374,-311.4139100250296,0.0037340886528045678,3.6812284577858385,0.19749090627178445,0.4093035122600183,0.0042149645256849,0.06446710805186301,249318.15999999997,3.335856810409666,1450000
31
+ 0.022532367975413716,1000.0,0.0,112.53350080430442,0.7443575124918804,-310.53070951049995,-0.019685822427794174,2.9280687405014265,0.20102749747946796,0.41651207765579423,0.004551605798815492,0.06708825426409343,249316.76000000007,3.336045575717802,1500000
32
+ 0.0226282863023132,622.9,227.3705565811018,69.43695476111398,27.427061901812312,-310.61101227966117,0.023847408688664768,4.072770034413283,0.20438095069006076,0.4243963984850058,0.0042967913230982984,0.06517232581478319,249329.98000000007,3.337735318778438,1550000
33
+ 0.02251756471101164,1000.0,0.0,113.1117727785198,0.708060597774811,-310.2097997894251,-0.009031136041321131,3.2831394941341876,0.20545002685412914,0.42870002132832746,0.004121883398037027,0.06380545026344177,249317.3,3.3361767819764827,1600000
34
+ 0.02324345225520488,1000.0,0.0,112.58783200810585,0.700254365674324,-309.81093734863185,0.010792187975272203,4.173983181090351,0.20954716698259154,0.43534422856629396,0.00407580781358689,0.06333609630123324,249311.46,3.3370296578350604,1650000
35
+ 0.023034302094988652,991.35,86.06641330972262,111.94574277277307,10.737232361132532,-309.82682270446486,-0.00998011765360852,3.4834142459702653,0.21182809635326294,0.44345493336826647,0.004230511846771744,0.06468436061496434,249317.95999999996,3.332694587054019,1700000
36
+ 0.02247516081634866,155.88,0.7520638270785266,13.932116551067054,0.6944454492909841,-309.6859475500498,0.011833161430805875,3.3866827291929655,0.21132846883475737,0.44311629195243224,0.004048434911436142,0.06325787430891879,249315.19999999992,3.335806387278181,1750000
37
+ 0.023582584492452596,1000.0,0.0,112.62695846443383,0.7738048985122458,-308.079643146361,0.023967845063880243,4.82795381976133,0.2192132819551235,0.46297640966445125,0.004588625703755808,0.067342728702041,249312.2000000001,3.3366384641819655,1800000
38
+ 0.02325382552251228,1000.0,0.0,112.25202610014446,0.7349891516714061,-308.59636667297707,-0.019277286837473893,3.695946204459705,0.21418838133484147,0.45037451347351126,0.0047196008580288875,0.06836702650894118,249320.20000000004,3.3385988586841346,1850000
39
+ 0.022774998246133223,486.05,419.9971279663707,52.67908524749579,49.74963904369347,-308.66431756896293,0.0034802978546920197,3.7490508135604355,0.21375725210070637,0.4508335244166867,0.004337091340820157,0.06546776551727393,249322.85999999996,3.329959851647623,1900000
40
+ 0.022895676686167536,1000.0,0.0,112.89270478408856,0.7268593183504022,-309.20872998840025,0.004254115152806044,3.2816691296976757,0.2129926963196709,0.4493999697513857,0.004281218249589776,0.0650689141312838,249313.22000000003,3.3324866855313853,1950000
41
+ 0.02280859014064094,129.27,0.968039255402383,10.92468468676285,0.7114037836021798,-308.59964009765554,0.0017859030930697701,3.7087599335134063,0.21895831488788364,0.4654109067490699,0.004272379959712152,0.06502229120078759,249308.73999999996,3.3296219424681057,2000000
42
+ 0.023072892904319055,1000.0,0.0,112.20943523878061,0.763073156601773,-307.97300786559623,0.0044813729035109925,3.925986793903753,0.21736304511517499,0.46533573924183735,0.00438895227882591,0.06589445048473479,249331.76,3.3310574809020728,2050000
43
+ 0.024493269150480956,1000.0,0.0,111.70093098630893,0.7338512385328116,-307.23827953612806,0.01045054016843396,5.135606085942931,0.22059210208058305,0.4710383708536648,0.004587764637551942,0.06726556087441964,249314.37999999995,3.332469714811175,2100000
44
+ 0.02234288464412064,1000.0,0.0,112.36050348407538,0.821340422639855,-306.8513868792731,-0.0034329189552366876,3.1013248471390753,0.21699746923893704,0.4585056991091385,0.004667516420946698,0.06792486803786134,249321.08000000007,3.3309149709374903,2150000
45
+ 0.023685001408569387,1000.0,0.0,111.71809424523833,0.7811256092965876,-307.1918517620894,0.060166101133674356,4.994275310803695,0.22187078694909854,0.4748869958466372,0.004552000955824868,0.06710348143424305,249314.84000000008,3.3325654801143982,2200000
46
+ 0.023443644662611157,704.09,412.2801012661174,77.87609536715084,48.58208671500185,-306.7830466632034,-0.04606622178345944,2.9132883391696005,0.2208351882898804,0.47600751709789046,0.004759337375243438,0.06863790326374423,249319.07999999996,3.3337692657319535,2250000
47
+ 0.023141479891576205,173.85,120.46670701899343,15.999218062023846,14.650360733312803,-307.4060339416522,0.0031095847160369874,3.5767947173166412,0.22116940156698348,0.4701705224031189,0.0046608414383848855,0.06794599086308802,249320.97999999992,3.3327654781705034,2300000
48
+ 0.02312315779924396,875.29,282.2559935590385,98.05623890018703,33.546505059468615,-307.4901295989987,-0.0025740141982586776,3.1920651794099912,0.2221457106956856,0.4750678829696748,0.00456436624117258,0.06724412068160265,249314.93999999994,3.3320544790273567,2350000
49
+ 0.02294915930688385,1000.0,0.0,112.79008929681606,0.7451500565005473,-307.06085521240755,-0.009619203246981099,3.7151525980389386,0.22107758990049303,0.4724674860835118,0.00437424553573081,0.06584526465170207,249321.16,3.33241729856819,2400000
50
+ 0.02205056494370099,677.75,403.04417561850465,75.13285539785427,47.84568927398814,-307.6256083367965,-0.0055938347651809965,3.351731815297012,0.21971015579432393,0.47034414393395607,0.004261761027286544,0.06496370416914841,249322.82,3.3336702946295915,2450000
51
+ 0.02194802405923621,1000.0,0.0,112.74556724325929,0.7648710067591363,-307.87778836974854,0.008843493604436491,3.3060069779771215,0.21917230700224907,0.46957634639412105,0.004676239928960562,0.0680814182456779,249325.13999999998,3.33145689313011,2500000
52
+ 0.02258766024369765,296.55,283.8258400850776,30.319008030912524,33.73241318548439,-307.0520387414567,0.003801723436936877,3.5833865315532774,0.2244978358051151,0.4792418472433075,0.004531830587799222,0.06701582455284368,249319.94,3.335511922055765,2550000
53
+ 0.022101059432178844,585.95,439.68562348569,64.49551010700915,52.051859772556966,-306.8015190649457,-0.004195353575795711,3.4606108810603438,0.22483434067785932,0.47894279302864917,0.00456495476910309,0.06727069576643242,249304.8,3.3299470324001943,2600000
54
+ 0.021810209825672257,1000.0,0.0,112.78861062227246,0.7616135528505342,-306.8183138751262,-0.009401344088017809,3.2840968597853335,0.22745234158724828,0.48913673693508,0.0044231929589491166,0.06619236980295473,249312.12000000005,3.3327870184081227,2650000
55
+ 0.021359386504255187,250.01,315.06131133479397,25.145873376127444,37.38621070955412,-306.88163599792705,-0.006554305549785408,3.120684218568787,0.22630259349763207,0.4853567671138014,0.004383134897670525,0.0659227243335503,249327.00000000015,3.330065312534705,2700000
56
+ 0.021253197911940296,983.97,112.21002227965198,110.96633651922166,13.76794532859752,-306.5623743780496,0.019910404346957712,3.249382778970589,0.230548255371749,0.49675962176650157,0.00456991347818336,0.067302645916792,249326.86000000007,3.3287006958240326,2750000
57
+ 0.020825102750398006,143.84,150.57175830812363,12.771242577861806,18.151734004325366,-305.92793435302065,-0.01138763914756502,3.7138658822715116,0.23362468388974394,0.5064686556983043,0.00472106190521534,0.06842156063168543,249305.86000000002,3.3263520921613106,2800000
58
+ 0.021513065361641312,116.57,0.9925220400575495,9.621345051725076,0.7167781379443986,-305.64207818725157,0.010528379181697859,3.566390829324717,0.23341762206763225,0.5028223622354704,0.004417640273648899,0.06618494028827525,249327.1,3.3284270149927253,2850000
59
+ 0.02127548562228675,161.76,192.3103803750593,14.878457078693252,23.081242523985942,-305.4825216461186,-0.019427686981410088,3.0743861699640544,0.23483648243904406,0.5071417501822241,0.004475365884871876,0.06661865633930296,249327.82000000004,3.328948825398771,2900000
60
+ 0.022079469101205083,514.9,438.79000672303374,56.018431868320626,51.77705815054844,-304.70285492797495,0.00805405898682782,3.4150326544642264,0.2401965307575462,0.515962885396483,0.004427081780594784,0.06626111305965096,249328.8800000001,3.329061546024718,2950000
61
+ 0.020972656999229875,559.21,440.790523831899,61.178927872258114,52.019004989654064,-303.6342569213868,0.026015410111919497,3.5955810888313775,0.24489083960443575,0.5275186316925411,0.00439581050774206,0.06603155463416358,249327.42,3.329856307787693,3000000