ppo-Huggy / run_logs /timers.json
mark-oppenheim's picture
Huggy1
4e09bbb
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4023927450180054,
"min": 1.4023927450180054,
"max": 1.428666114807129,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70666.5703125,
"min": 67916.0625,
"max": 78361.015625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 76.54813664596273,
"min": 74.65454545454546,
"max": 381.18939393939394,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49297.0,
"min": 48776.0,
"max": 50317.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999905.0,
"min": 49838.0,
"max": 1999905.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999905.0,
"min": 49838.0,
"max": 1999905.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4634532928466797,
"min": 0.07409073412418365,
"max": 2.4926908016204834,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1586.4638671875,
"min": 9.705885887145996,
"max": 1633.704833984375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8452348545286226,
"min": 1.8056754741732401,
"max": 3.966923669201538,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2476.331246316433,
"min": 236.54348711669445,
"max": 2533.460683941841,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8452348545286226,
"min": 1.8056754741732401,
"max": 3.966923669201538,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2476.331246316433,
"min": 236.54348711669445,
"max": 2533.460683941841,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.018753623090580932,
"min": 0.013041378177715363,
"max": 0.019428870390765948,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0562608692717428,
"min": 0.029558640886777236,
"max": 0.056968151134302994,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05571267762117915,
"min": 0.021551685376713675,
"max": 0.06307463633517424,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16713803286353746,
"min": 0.04310337075342735,
"max": 0.17724083823462328,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.83334872225001e-06,
"min": 3.83334872225001e-06,
"max": 0.0002952926265691249,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1500046166750029e-05,
"min": 1.1500046166750029e-05,
"max": 0.00084427426857525,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10127774999999999,
"min": 0.10127774999999999,
"max": 0.198430875,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30383324999999994,
"min": 0.20772209999999997,
"max": 0.58142475,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.375972500000018e-05,
"min": 7.375972500000018e-05,
"max": 0.0049217006625,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022127917500000053,
"min": 0.00022127917500000053,
"max": 0.014073095025,
"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": "1688910290",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1688912819"
},
"total": 2529.373878372,
"count": 1,
"self": 0.43276333599987993,
"children": {
"run_training.setup": {
"total": 0.04584082500002751,
"count": 1,
"self": 0.04584082500002751
},
"TrainerController.start_learning": {
"total": 2528.895274211,
"count": 1,
"self": 4.616170913918268,
"children": {
"TrainerController._reset_env": {
"total": 4.260226791000036,
"count": 1,
"self": 4.260226791000036
},
"TrainerController.advance": {
"total": 2519.8942593730812,
"count": 233084,
"self": 4.754177730229912,
"children": {
"env_step": {
"total": 1949.937788084984,
"count": 233084,
"self": 1645.4839071570977,
"children": {
"SubprocessEnvManager._take_step": {
"total": 301.54759783190707,
"count": 233084,
"self": 17.51255457187608,
"children": {
"TorchPolicy.evaluate": {
"total": 284.035043260031,
"count": 222928,
"self": 284.035043260031
}
}
},
"workers": {
"total": 2.9062830959793473,
"count": 233084,
"self": 0.0,
"children": {
"worker_root": {
"total": 2520.806786622959,
"count": 233084,
"is_parallel": true,
"self": 1176.9891585748794,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009351659999765616,
"count": 1,
"is_parallel": true,
"self": 0.00023986199994396884,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006953040000325927,
"count": 2,
"is_parallel": true,
"self": 0.0006953040000325927
}
}
},
"UnityEnvironment.step": {
"total": 0.030052511000008053,
"count": 1,
"is_parallel": true,
"self": 0.00037834400006886426,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020573699998749362,
"count": 1,
"is_parallel": true,
"self": 0.00020573699998749362
},
"communicator.exchange": {
"total": 0.028668512999956874,
"count": 1,
"is_parallel": true,
"self": 0.028668512999956874
},
"steps_from_proto": {
"total": 0.0007999169999948208,
"count": 1,
"is_parallel": true,
"self": 0.0002336999998533429,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005662170001414779,
"count": 2,
"is_parallel": true,
"self": 0.0005662170001414779
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1343.8176280480795,
"count": 233083,
"is_parallel": true,
"self": 41.02023794409547,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.09771876699483,
"count": 233083,
"is_parallel": true,
"self": 82.09771876699483
},
"communicator.exchange": {
"total": 1119.8244315010174,
"count": 233083,
"is_parallel": true,
"self": 1119.8244315010174
},
"steps_from_proto": {
"total": 100.8752398359718,
"count": 233083,
"is_parallel": true,
"self": 34.88592472508981,
"children": {
"_process_rank_one_or_two_observation": {
"total": 65.98931511088199,
"count": 466166,
"is_parallel": true,
"self": 65.98931511088199
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 565.2022935578674,
"count": 233084,
"self": 7.028935943815782,
"children": {
"process_trajectory": {
"total": 148.49611751905127,
"count": 233084,
"self": 146.94237280705102,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5537447120002525,
"count": 10,
"self": 1.5537447120002525
}
}
},
"_update_policy": {
"total": 409.67724009500034,
"count": 97,
"self": 347.1997059189872,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.47753417601314,
"count": 2910,
"self": 62.47753417601314
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1920001270482317e-06,
"count": 1,
"self": 1.1920001270482317e-06
},
"TrainerController._save_models": {
"total": 0.12461594100022921,
"count": 1,
"self": 0.002156687000478996,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12245925399975022,
"count": 1,
"self": 0.12245925399975022
}
}
}
}
}
}
}