| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.37633004784584045, |
| "min": 0.37633004784584045, |
| "max": 1.4875518083572388, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 11271.837890625, |
| "min": 11271.837890625, |
| "max": 45126.37109375, |
| "count": 33 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 989941.0, |
| "min": 29952.0, |
| "max": 989941.0, |
| "count": 33 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 989941.0, |
| "min": 29952.0, |
| "max": 989941.0, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.5358343720436096, |
| "min": -0.1610211580991745, |
| "max": 0.6084722876548767, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 145.21112060546875, |
| "min": -38.16201400756836, |
| "max": 169.15528869628906, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.020127693191170692, |
| "min": -0.014595001004636288, |
| "max": 0.21314296126365662, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 5.4546051025390625, |
| "min": -4.05741024017334, |
| "max": 51.15431213378906, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06929623967430198, |
| "min": 0.06426746996502126, |
| "max": 0.07512623408739723, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9701473554402278, |
| "min": 0.5258836386117806, |
| "max": 1.0712396885033277, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.018229874855716754, |
| "min": 0.0014277781853121458, |
| "max": 0.01852261415171799, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.25521824798003456, |
| "min": 0.019066859170885034, |
| "max": 0.27783921227576985, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 7.665976016135714e-06, |
| "min": 7.665976016135714e-06, |
| "max": 0.00029515063018788575, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.00010732366422589999, |
| "min": 0.00010732366422589999, |
| "max": 0.0036352966882345, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10255529285714284, |
| "min": 0.10255529285714284, |
| "max": 0.19838354285714285, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4357740999999997, |
| "min": 1.3886848, |
| "max": 2.611765500000001, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.0002652737564285714, |
| "min": 0.0002652737564285714, |
| "max": 0.00983851593142857, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.00371383259, |
| "min": 0.00371383259, |
| "max": 0.12119537344999999, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.008127506822347641, |
| "min": 0.007846963591873646, |
| "max": 0.3542431890964508, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.11378509551286697, |
| "min": 0.1098574846982956, |
| "max": 2.4797022342681885, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 321.8068181818182, |
| "min": 308.7938144329897, |
| "max": 999.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 28319.0, |
| "min": 15984.0, |
| "max": 32752.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.6099977005611767, |
| "min": -1.0000000521540642, |
| "max": 1.644166296406796, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 141.67979764938354, |
| "min": -29.96900161355734, |
| "max": 156.31739829480648, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.6099977005611767, |
| "min": -1.0000000521540642, |
| "max": 1.644166296406796, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 141.67979764938354, |
| "min": -29.96900161355734, |
| "max": 156.31739829480648, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.027230969816049434, |
| "min": 0.02630970784866804, |
| "max": 7.5256711486727, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 2.39632534381235, |
| "min": 2.39632534381235, |
| "max": 120.4107383787632, |
| "count": 33 |
| }, |
| "Pyramids.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 33 |
| }, |
| "Pyramids.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 33 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1794057671", |
| "python_version": "3.10.11 (main, May 7 2023, 19:26:31) [Clang 16.0.3 ]", |
| "command_line_arguments": "/content/ml-agents/ml-agents/mlagents/trainers/learn.py ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --results-dir=/content/drive/MyDrive/mlagents-results --no-graphics", |
| "mlagents_version": "1.2.0.dev0", |
| "mlagents_envs_version": "1.2.0.dev0", |
| "communication_protocol_version": "1.5.0", |
| "pytorch_version": "2.8.0+cu128", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1794060332" |
| }, |
| "total": 2660.358873241, |
| "count": 1, |
| "self": 0.5538324019998981, |
| "children": { |
| "run_training.setup": { |
| "total": 0.18442634400003044, |
| "count": 1, |
| "self": 0.18442634400003044 |
| }, |
| "TrainerController.start_learning": { |
| "total": 2659.620614495, |
| "count": 1, |
| "self": 1.6048606709400701, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 2.6510830449999503, |
| "count": 1, |
| "self": 2.6510830449999503 |
| }, |
| "TrainerController.advance": { |
| "total": 2655.2013794370596, |
| "count": 63951, |
| "self": 1.585520835033094, |
| "children": { |
| "env_step": { |
| "total": 1954.8188955480111, |
| "count": 63951, |
| "self": 1787.3547704291045, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 166.51879851396757, |
| "count": 63951, |
| "self": 5.030901460954738, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 161.48789705301283, |
| "count": 62554, |
| "self": 161.48789705301283 |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.945326604939055, |
| "count": 63951, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 2652.663708226967, |
| "count": 63951, |
| "is_parallel": true, |
| "self": 992.6108869369491, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0019053790001635207, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0007013920003373642, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0012039869998261565, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0012039869998261565 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.049287651999975424, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.000545470999668396, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.00046640400000796944, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00046640400000796944 |
| }, |
| "communicator.exchange": { |
| "total": 0.046443502000101944, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.046443502000101944 |
| }, |
| "steps_from_proto": { |
| "total": 0.0018322750001971144, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0004075150009157369, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0014247599992813775, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0014247599992813775 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1660.052821290018, |
| "count": 63950, |
| "is_parallel": true, |
| "self": 35.577454165044855, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 24.09703935699622, |
| "count": 63950, |
| "is_parallel": true, |
| "self": 24.09703935699622 |
| }, |
| "communicator.exchange": { |
| "total": 1482.4013122680096, |
| "count": 63950, |
| "is_parallel": true, |
| "self": 1482.4013122680096 |
| }, |
| "steps_from_proto": { |
| "total": 117.97701549996737, |
| "count": 63950, |
| "is_parallel": true, |
| "self": 25.35405992662004, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 92.62295557334733, |
| "count": 511600, |
| "is_parallel": true, |
| "self": 92.62295557334733 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 698.7969630540154, |
| "count": 63951, |
| "self": 2.8471579760432633, |
| "children": { |
| "process_trajectory": { |
| "total": 127.65272777196856, |
| "count": 63951, |
| "self": 127.24681907296849, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.4059086990000651, |
| "count": 2, |
| "self": 0.4059086990000651 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 568.2970773060035, |
| "count": 453, |
| "self": 316.43434619897494, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 251.8627311070286, |
| "count": 22776, |
| "self": 251.8627311070286 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.1190004443051293e-06, |
| "count": 1, |
| "self": 1.1190004443051293e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.16329022300033103, |
| "count": 1, |
| "self": 0.012301925000429037, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.150988297999902, |
| "count": 1, |
| "self": 0.150988297999902 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
