thanhkt's picture
Upload eval from run_all.sh
c24a8ae verified
Raw History Blame Contribute Delete
19.4 kB
{
"per_task": [
{
"task_group": "pusht",
"task_id": 0,
"metrics": {
"sum_rewards": [
153.26045796844588,
80.23884581662739,
126.46531182239728,
230.81533440214434,
107.04251739480375,
110.66629282485894,
54.77157956367507,
31.736423538391485,
72.63271346093859,
71.63564968980288,
191.34465521980172,
0.9023674371722685,
66.87744629986526,
54.52109439250796,
159.61683385862125,
229.8311776590328,
149.87421404912672,
148.45101159347251,
29.310644511264826,
64.1006599470841,
25.966400668631866,
58.21529063157871,
142.80553977728968,
124.1219706072975,
200.99030373003401,
108.37313699864696,
131.5453651050214,
97.92924145460705,
60.906515863680724,
86.74928675589588,
77.46870387404792,
200.5646563949116,
118.06952484457337,
0.01423175339769715,
96.94741116348487,
17.69349459931778,
38.19104126502981,
121.92373036133631,
2.9781706270268042,
105.91449843202881,
219.79311881011785,
122.44891142082454,
110.11877532553324,
1.7601410285686538,
27.975051251735817,
217.2043521885377,
145.03708749081048,
0.5488142468312367,
0.0,
47.911992459278366,
87.79045968290836,
175.93190032328326,
94.23671970014733,
196.0216169010793,
40.391723123907205,
70.96398336607508,
154.58900673857062,
182.48762157423965,
49.64083848072846,
183.1457628208239,
0.7651475128858292,
78.65467927797208,
55.79735098348628,
131.00096685664684,
87.36275846152374,
47.5800776882251,
179.7675994597243,
203.14951625143456,
0.0,
4.522328130092332,
123.31489890999012,
0.0,
33.01018873014799,
99.00147563562483,
121.87558537764046,
62.2409056876037,
31.664081965570187,
151.33117259683326,
144.55305053975871,
113.01864968439439,
61.72807615259994,
35.10915985741088,
156.60683347590512,
79.0957375781442,
0.0,
76.46567612850937,
202.20043882723587,
149.4640000069527,
24.356887015158257,
83.38947772055485,
179.52137765232663,
193.35843198354837,
101.66782780405937,
0.4563830209850856,
67.07755665339934,
201.14217283881436,
88.39749098854287,
151.1881593127129,
59.54967610430161,
103.8738270155542,
27.910329727206232,
0.0,
47.35935711339584,
40.83589307317217,
0.32805385066051435,
142.83417118237153,
103.2410263156449,
157.0043681249084,
0.0,
199.97934544745868,
86.61207202081016,
0.0,
115.23437931590057,
114.57765936858186,
39.44837938042828,
144.8307729451703,
117.75347512589225,
0.24710316922803527,
45.824223621111145,
132.8547606077669,
130.38156989858032,
40.19954306219073,
186.36384483404558,
112.13121981619774,
20.72099299092352,
194.3904435534996,
188.88105535424643,
175.05214559111505,
122.61703108275336,
104.46800050144759,
56.08262904607086,
83.10610506290429,
8.875564602457116,
55.49266323517287,
123.24795037736891,
51.5826911363905,
131.81682620186993,
0.0,
201.74552954438323,
176.17318643269772,
150.88756649552914,
103.20665587706065,
51.45396158063054,
115.21419801538909,
92.33508140800242,
0.0,
128.98679602089567,
46.214720067176124,
178.6462672877447,
50.94578994307002,
0.0,
177.3283112071994,
66.62126546537199,
59.871882032324706,
41.90428150083431,
86.66660965502973,
37.746213222139446,
157.89661888483573,
135.9311238496662,
215.75974742969436,
111.93034981380079,
168.3631160641409,
51.266586040555694,
66.97935534412989,
36.39534958347183,
19.952722319368924,
209.12712217491088,
57.94129781629592,
79.96054204828184,
94.24228322176356,
90.672053322838,
216.7578580694954,
65.45837062810295,
213.6748559252736,
31.313388968517938,
207.4448435031523,
84.01011498139653,
10.09369525111676,
165.36997747563947,
62.052551231265404,
149.7493989205779,
105.36127848454242,
66.32317497251103,
196.72064627146813,
195.01273908715342,
80.49205075517852,
73.08971204826183,
139.62482966571702,
106.33656180732471,
116.58034857625532,
47.92866662950415,
67.40153865871547,
213.46868604561968,
52.24822116930357,
123.67056320516535,
0.5635346082656544,
130.91911007849944,
51.19901399983114,
65.86227087129772,
131.83188198088402
],
"max_rewards": [
0.9561299153634272,
0.4537152667358446,
1.0,
0.9913778576243112,
0.9581444915197966,
1.0,
0.42890776130576286,
1.0,
0.5173915143022643,
0.5116611417052493,
0.9599263233972201,
0.14425333826550865,
1.0,
1.0,
0.9717245076154153,
0.982032123646803,
0.9463500435867451,
0.9802425266885876,
1.0,
1.0,
0.5260259064810713,
0.9236329394610595,
0.9751021558076928,
0.9883947059158679,
0.9821144300310523,
0.5739906608632641,
0.6998037577339975,
1.0,
1.0,
0.5645698762925706,
0.9490946005959958,
0.9641944447206269,
0.5101092867961573,
0.010735535622975606,
1.0,
1.0,
1.0,
1.0,
0.10134233957711135,
1.0,
0.9966034180808157,
0.6269506157723178,
1.0,
0.11217754438784838,
0.44783078841734353,
0.9843640701513408,
0.9732302852611326,
0.03846418379283366,
0.0,
1.0,
1.0,
1.0,
1.0,
0.9855822151158238,
0.9234171374357959,
1.0,
0.9984267899031605,
0.9702406439363543,
1.0,
0.9084914781510816,
0.03122945857387656,
1.0,
1.0,
1.0,
0.8422819206276831,
0.5607483592244442,
0.9808391292452026,
0.9911358089782675,
0.0,
0.24650267388827285,
0.993349364861063,
0.0,
1.0,
1.0,
1.0,
1.0,
1.0,
0.9624839950062926,
0.991689049566255,
1.0,
0.9181954142528358,
1.0,
0.9706559169318558,
0.5129802053914668,
0.0,
1.0,
0.9836529933910765,
0.9748531137285875,
0.7719686264141027,
0.9440256690151938,
0.997552699388021,
0.9010255280473648,
1.0,
0.029210672252293637,
1.0,
0.9796712082415895,
1.0,
0.6572157766381012,
1.0,
1.0,
1.0,
0.0,
1.0,
1.0,
0.060782778709482004,
1.0,
0.616491188262692,
0.6073596582510397,
0.0,
0.9625219170004464,
1.0,
0.0,
0.9746961917840774,
0.9705547949247064,
1.0,
0.9628706550110476,
0.985103038178101,
0.0529796185895799,
1.0,
1.0,
1.0,
1.0,
0.980942943458687,
0.6177651714629965,
0.5785745684212884,
0.980481974536058,
0.9778835359635747,
0.9992427972862153,
0.5416825728656843,
1.0,
1.0,
1.0,
0.6445054620861609,
1.0,
0.9644935421657714,
1.0,
0.9537636904607543,
0.0,
0.9844983281836601,
0.9405474481568148,
0.9322852634611546,
0.7063972701895324,
1.0,
0.8587289637519382,
1.0,
0.0,
0.9372846531570669,
0.41470479545654526,
0.721417139106359,
1.0,
0.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
0.997762514809229,
0.9862425723961641,
0.9875883743311951,
0.4270234867863063,
0.9932565421102384,
0.5052889067097802,
1.0,
1.0,
0.4273765780690916,
0.9880294343844742,
1.0,
0.7789044001678301,
0.8638977910027278,
0.6432675930823181,
0.9988333088416881,
0.9975410748459719,
0.9923586243524826,
1.0,
0.9541509545971721,
1.0,
0.41840268189458013,
0.6921399169742072,
0.5156012216233201,
1.0,
0.7905137079299466,
1.0,
0.9587424595302427,
0.950375123141353,
1.0,
1.0,
0.9728976819296193,
0.9736881755695568,
0.9862504059406834,
1.0,
0.4622487450709938,
0.9718091723721238,
1.0,
0.551704896811438,
0.131840342618754,
0.6344656674534601,
1.0,
0.7847169104040569,
1.0
],
"successes": [
false,
false,
true,
false,
false,
true,
false,
true,
false,
false,
false,
false,
true,
true,
false,
false,
false,
false,
true,
true,
false,
false,
false,
false,
false,
false,
false,
true,
true,
false,
false,
false,
false,
false,
true,
true,
true,
true,
false,
true,
false,
false,
true,
false,
false,
false,
false,
false,
false,
true,
true,
true,
true,
false,
false,
true,
false,
false,
true,
false,
false,
true,
true,
true,
false,
false,
false,
false,
false,
false,
false,
false,
true,
true,
true,
true,
true,
false,
false,
true,
false,
true,
false,
false,
false,
true,
false,
false,
false,
false,
false,
false,
true,
false,
true,
false,
true,
false,
true,
true,
true,
false,
true,
true,
false,
true,
false,
false,
false,
false,
true,
false,
false,
false,
true,
false,
false,
false,
true,
true,
true,
true,
false,
false,
false,
false,
false,
false,
false,
true,
true,
true,
false,
true,
false,
true,
false,
false,
false,
false,
false,
false,
true,
false,
true,
false,
false,
false,
false,
true,
false,
true,
true,
true,
true,
true,
true,
false,
false,
false,
false,
false,
false,
true,
true,
false,
false,
true,
false,
false,
false,
false,
false,
false,
true,
false,
true,
false,
false,
false,
true,
false,
true,
false,
false,
true,
true,
false,
false,
false,
true,
false,
false,
true,
false,
false,
false,
true,
false,
true
],
"video_paths": [
"/home/25thanh.tk/plan-bind/experiments/261028-plan-bind-d3-pusht/outputs/full/eval/diffusion_L0_s1001/videos/pusht_0/eval_episode_0.mp4",
"/home/25thanh.tk/plan-bind/experiments/261028-plan-bind-d3-pusht/outputs/full/eval/diffusion_L0_s1001/videos/pusht_0/eval_episode_1.mp4",
"/home/25thanh.tk/plan-bind/experiments/261028-plan-bind-d3-pusht/outputs/full/eval/diffusion_L0_s1001/videos/pusht_0/eval_episode_2.mp4",
"/home/25thanh.tk/plan-bind/experiments/261028-plan-bind-d3-pusht/outputs/full/eval/diffusion_L0_s1001/videos/pusht_0/eval_episode_3.mp4",
"/home/25thanh.tk/plan-bind/experiments/261028-plan-bind-d3-pusht/outputs/full/eval/diffusion_L0_s1001/videos/pusht_0/eval_episode_4.mp4",
"/home/25thanh.tk/plan-bind/experiments/261028-plan-bind-d3-pusht/outputs/full/eval/diffusion_L0_s1001/videos/pusht_0/eval_episode_5.mp4",
"/home/25thanh.tk/plan-bind/experiments/261028-plan-bind-d3-pusht/outputs/full/eval/diffusion_L0_s1001/videos/pusht_0/eval_episode_6.mp4",
"/home/25thanh.tk/plan-bind/experiments/261028-plan-bind-d3-pusht/outputs/full/eval/diffusion_L0_s1001/videos/pusht_0/eval_episode_7.mp4",
"/home/25thanh.tk/plan-bind/experiments/261028-plan-bind-d3-pusht/outputs/full/eval/diffusion_L0_s1001/videos/pusht_0/eval_episode_8.mp4",
"/home/25thanh.tk/plan-bind/experiments/261028-plan-bind-d3-pusht/outputs/full/eval/diffusion_L0_s1001/videos/pusht_0/eval_episode_9.mp4"
],
"predicted_video_paths": []
},
"n_episodes": 200,
"n_success": 74,
"pc_success": 37.0,
"pc_success_ci95": [
30.61260840985912,
43.877370075949806
]
}
],
"per_group": {
"pusht": {
"avg_sum_reward": 97.48966680727179,
"avg_max_reward": 0.8102174671617927,
"pc_success": 37.0,
"n_episodes": 200,
"n_success": 74,
"pc_success_ci95": [
30.61260840985912,
43.877370075949806
],
"video_paths": [
"/home/25thanh.tk/plan-bind/experiments/261028-plan-bind-d3-pusht/outputs/full/eval/diffusion_L0_s1001/videos/pusht_0/eval_episode_0.mp4",
"/home/25thanh.tk/plan-bind/experiments/261028-plan-bind-d3-pusht/outputs/full/eval/diffusion_L0_s1001/videos/pusht_0/eval_episode_1.mp4",
"/home/25thanh.tk/plan-bind/experiments/261028-plan-bind-d3-pusht/outputs/full/eval/diffusion_L0_s1001/videos/pusht_0/eval_episode_2.mp4",
"/home/25thanh.tk/plan-bind/experiments/261028-plan-bind-d3-pusht/outputs/full/eval/diffusion_L0_s1001/videos/pusht_0/eval_episode_3.mp4",
"/home/25thanh.tk/plan-bind/experiments/261028-plan-bind-d3-pusht/outputs/full/eval/diffusion_L0_s1001/videos/pusht_0/eval_episode_4.mp4",
"/home/25thanh.tk/plan-bind/experiments/261028-plan-bind-d3-pusht/outputs/full/eval/diffusion_L0_s1001/videos/pusht_0/eval_episode_5.mp4",
"/home/25thanh.tk/plan-bind/experiments/261028-plan-bind-d3-pusht/outputs/full/eval/diffusion_L0_s1001/videos/pusht_0/eval_episode_6.mp4",
"/home/25thanh.tk/plan-bind/experiments/261028-plan-bind-d3-pusht/outputs/full/eval/diffusion_L0_s1001/videos/pusht_0/eval_episode_7.mp4",
"/home/25thanh.tk/plan-bind/experiments/261028-plan-bind-d3-pusht/outputs/full/eval/diffusion_L0_s1001/videos/pusht_0/eval_episode_8.mp4",
"/home/25thanh.tk/plan-bind/experiments/261028-plan-bind-d3-pusht/outputs/full/eval/diffusion_L0_s1001/videos/pusht_0/eval_episode_9.mp4"
],
"predicted_video_paths": []
}
},
"overall": {
"avg_sum_reward": 97.48966680727179,
"avg_max_reward": 0.8102174671617927,
"pc_success": 37.0,
"n_episodes": 200,
"n_success": 74,
"pc_success_ci95": [
30.61260840985912,
43.877370075949806
],
"eval_s": 274.93339109420776,
"eval_ep_s": 1.3746669566631318,
"video_paths": [
"/home/25thanh.tk/plan-bind/experiments/261028-plan-bind-d3-pusht/outputs/full/eval/diffusion_L0_s1001/videos/pusht_0/eval_episode_0.mp4",
"/home/25thanh.tk/plan-bind/experiments/261028-plan-bind-d3-pusht/outputs/full/eval/diffusion_L0_s1001/videos/pusht_0/eval_episode_1.mp4",
"/home/25thanh.tk/plan-bind/experiments/261028-plan-bind-d3-pusht/outputs/full/eval/diffusion_L0_s1001/videos/pusht_0/eval_episode_2.mp4",
"/home/25thanh.tk/plan-bind/experiments/261028-plan-bind-d3-pusht/outputs/full/eval/diffusion_L0_s1001/videos/pusht_0/eval_episode_3.mp4",
"/home/25thanh.tk/plan-bind/experiments/261028-plan-bind-d3-pusht/outputs/full/eval/diffusion_L0_s1001/videos/pusht_0/eval_episode_4.mp4",
"/home/25thanh.tk/plan-bind/experiments/261028-plan-bind-d3-pusht/outputs/full/eval/diffusion_L0_s1001/videos/pusht_0/eval_episode_5.mp4",
"/home/25thanh.tk/plan-bind/experiments/261028-plan-bind-d3-pusht/outputs/full/eval/diffusion_L0_s1001/videos/pusht_0/eval_episode_6.mp4",
"/home/25thanh.tk/plan-bind/experiments/261028-plan-bind-d3-pusht/outputs/full/eval/diffusion_L0_s1001/videos/pusht_0/eval_episode_7.mp4",
"/home/25thanh.tk/plan-bind/experiments/261028-plan-bind-d3-pusht/outputs/full/eval/diffusion_L0_s1001/videos/pusht_0/eval_episode_8.mp4",
"/home/25thanh.tk/plan-bind/experiments/261028-plan-bind-d3-pusht/outputs/full/eval/diffusion_L0_s1001/videos/pusht_0/eval_episode_9.mp4"
],
"predicted_video_paths": []
}
}