ppo-Huggy / run_logs /timers.json
othorizedshogun's picture
Huggy
4ed17fd verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4016460180282593,
"min": 1.4016460180282593,
"max": 1.4267702102661133,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68593.75,
"min": 68046.125,
"max": 77722.8984375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 100.99392712550608,
"min": 84.14551607445009,
"max": 400.384,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49891.0,
"min": 49076.0,
"max": 50048.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999672.0,
"min": 49581.0,
"max": 1999672.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999672.0,
"min": 49581.0,
"max": 1999672.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.438096523284912,
"min": 0.07987549155950546,
"max": 2.466733455657959,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1204.419677734375,
"min": 9.904561042785645,
"max": 1436.4970703125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.784825221005722,
"min": 1.7073551615880382,
"max": 3.9169878938448117,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1869.7036591768265,
"min": 211.71204003691673,
"max": 2293.3561337590218,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.784825221005722,
"min": 1.7073551615880382,
"max": 3.9169878938448117,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1869.7036591768265,
"min": 211.71204003691673,
"max": 2293.3561337590218,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.018452946662970742,
"min": 0.013527977550014232,
"max": 0.019316639330160493,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.036905893325941484,
"min": 0.027055955100028464,
"max": 0.05772842355509056,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0494752703855435,
"min": 0.021344922482967377,
"max": 0.06490496415644884,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.098950540771087,
"min": 0.04268984496593475,
"max": 0.18273058844109374,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.592198469300004e-06,
"min": 4.592198469300004e-06,
"max": 0.00029529742656752504,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.184396938600008e-06,
"min": 9.184396938600008e-06,
"max": 0.0008437726687424501,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10153070000000003,
"min": 0.10153070000000003,
"max": 0.19843247499999994,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20306140000000006,
"min": 0.20306140000000006,
"max": 0.5812575500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.63819300000001e-05,
"min": 8.63819300000001e-05,
"max": 0.0049217805025000005,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001727638600000002,
"min": 0.0001727638600000002,
"max": 0.014064751745,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1723893091",
"python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1723895631"
},
"total": 2539.677646611,
"count": 1,
"self": 0.4415991560003931,
"children": {
"run_training.setup": {
"total": 0.06005840099987836,
"count": 1,
"self": 0.06005840099987836
},
"TrainerController.start_learning": {
"total": 2539.1759890539997,
"count": 1,
"self": 4.690578329988966,
"children": {
"TrainerController._reset_env": {
"total": 2.8309735140001067,
"count": 1,
"self": 2.8309735140001067
},
"TrainerController.advance": {
"total": 2531.5353492180107,
"count": 232255,
"self": 4.892055597823855,
"children": {
"env_step": {
"total": 2011.2116296850804,
"count": 232255,
"self": 1660.3453432329197,
"children": {
"SubprocessEnvManager._take_step": {
"total": 347.76700512103366,
"count": 232255,
"self": 17.505588513992734,
"children": {
"TorchPolicy.evaluate": {
"total": 330.2614166070409,
"count": 222928,
"self": 330.2614166070409
}
}
},
"workers": {
"total": 3.099281331127031,
"count": 232255,
"self": 0.0,
"children": {
"worker_root": {
"total": 2531.565013734953,
"count": 232255,
"is_parallel": true,
"self": 1192.576003690989,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.000929394999957367,
"count": 1,
"is_parallel": true,
"self": 0.0002608119998512848,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006685830001060822,
"count": 2,
"is_parallel": true,
"self": 0.0006685830001060822
}
}
},
"UnityEnvironment.step": {
"total": 0.030437441999993098,
"count": 1,
"is_parallel": true,
"self": 0.0003731040001184738,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002556609999828652,
"count": 1,
"is_parallel": true,
"self": 0.0002556609999828652
},
"communicator.exchange": {
"total": 0.02898328199989919,
"count": 1,
"is_parallel": true,
"self": 0.02898328199989919
},
"steps_from_proto": {
"total": 0.000825394999992568,
"count": 1,
"is_parallel": true,
"self": 0.00021562599999924714,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006097689999933209,
"count": 2,
"is_parallel": true,
"self": 0.0006097689999933209
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1338.989010043964,
"count": 232254,
"is_parallel": true,
"self": 39.72533374801287,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 88.05978458900677,
"count": 232254,
"is_parallel": true,
"self": 88.05978458900677
},
"communicator.exchange": {
"total": 1115.3692329899634,
"count": 232254,
"is_parallel": true,
"self": 1115.3692329899634
},
"steps_from_proto": {
"total": 95.83465871698104,
"count": 232254,
"is_parallel": true,
"self": 36.1179346390054,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.71672407797564,
"count": 464508,
"is_parallel": true,
"self": 59.71672407797564
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 515.4316639351064,
"count": 232255,
"self": 7.3613917839893475,
"children": {
"process_trajectory": {
"total": 166.17606772911472,
"count": 232255,
"self": 164.76248388011413,
"children": {
"RLTrainer._checkpoint": {
"total": 1.413583849000588,
"count": 10,
"self": 1.413583849000588
}
}
},
"_update_policy": {
"total": 341.8942044220023,
"count": 96,
"self": 277.24882211499335,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.64538230700896,
"count": 2880,
"self": 64.64538230700896
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.820002221909817e-07,
"count": 1,
"self": 8.820002221909817e-07
},
"TrainerController._save_models": {
"total": 0.11908710999978211,
"count": 1,
"self": 0.0028622769996218267,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11622483300016029,
"count": 1,
"self": 0.11622483300016029
}
}
}
}
}
}
}