ppo-Huggy / run_logs /timers.json
ospeek's picture
Huggy
0cafe5f
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4028151035308838,
"min": 1.4028151035308838,
"max": 1.4288065433502197,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71218.1171875,
"min": 69060.796875,
"max": 77591.2265625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 75.66257668711657,
"min": 67.70027624309392,
"max": 386.0615384615385,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49332.0,
"min": 49015.0,
"max": 50188.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999879.0,
"min": 49568.0,
"max": 1999879.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999879.0,
"min": 49568.0,
"max": 1999879.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.487884044647217,
"min": 0.09975283592939377,
"max": 2.53963041305542,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1622.1004638671875,
"min": 12.868115425109863,
"max": 1801.9638671875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7573663654502916,
"min": 1.862935187396153,
"max": 4.105184104697795,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2449.80287027359,
"min": 240.31863917410374,
"max": 2817.628917992115,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7573663654502916,
"min": 1.862935187396153,
"max": 4.105184104697795,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2449.80287027359,
"min": 240.31863917410374,
"max": 2817.628917992115,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016453603361878778,
"min": 0.012736963199859019,
"max": 0.020758286939235406,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.049360810085636336,
"min": 0.025473926399718037,
"max": 0.057723179733390376,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0635308405591382,
"min": 0.02178633517275254,
"max": 0.0635308405591382,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.19059252167741458,
"min": 0.04357267034550508,
"max": 0.19059252167741458,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.855348714916664e-06,
"min": 3.855348714916664e-06,
"max": 0.0002953488765503749,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1566046144749992e-05,
"min": 1.1566046144749992e-05,
"max": 0.0008439088686970499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10128508333333332,
"min": 0.10128508333333332,
"max": 0.19844962499999996,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30385524999999997,
"min": 0.20772489999999996,
"max": 0.5813029500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.412565833333332e-05,
"min": 7.412565833333332e-05,
"max": 0.004922636287499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022237697499999997,
"min": 0.00022237697499999997,
"max": 0.014067017205,
"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": "1673107094",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1673109261"
},
"total": 2166.665210557,
"count": 1,
"self": 0.3908150500001284,
"children": {
"run_training.setup": {
"total": 0.10369133599999714,
"count": 1,
"self": 0.10369133599999714
},
"TrainerController.start_learning": {
"total": 2166.170704171,
"count": 1,
"self": 3.652257801029009,
"children": {
"TrainerController._reset_env": {
"total": 7.95051317299999,
"count": 1,
"self": 7.95051317299999
},
"TrainerController.advance": {
"total": 2154.4485887409714,
"count": 233957,
"self": 3.9054755749971264,
"children": {
"env_step": {
"total": 1680.0782644619558,
"count": 233957,
"self": 1413.1094284969824,
"children": {
"SubprocessEnvManager._take_step": {
"total": 264.42106964102754,
"count": 233957,
"self": 13.947094889975233,
"children": {
"TorchPolicy.evaluate": {
"total": 250.4739747510523,
"count": 223030,
"self": 63.49317543903635,
"children": {
"TorchPolicy.sample_actions": {
"total": 186.98079931201596,
"count": 223030,
"self": 186.98079931201596
}
}
}
}
},
"workers": {
"total": 2.5477663239457797,
"count": 233957,
"self": 0.0,
"children": {
"worker_root": {
"total": 2158.669352113948,
"count": 233957,
"is_parallel": true,
"self": 993.4299178949343,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0020922900000641675,
"count": 1,
"is_parallel": true,
"self": 0.00028018800003337674,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018121020000307908,
"count": 2,
"is_parallel": true,
"self": 0.0018121020000307908
}
}
},
"UnityEnvironment.step": {
"total": 0.02613750299997264,
"count": 1,
"is_parallel": true,
"self": 0.000263822000079017,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019572099995457393,
"count": 1,
"is_parallel": true,
"self": 0.00019572099995457393
},
"communicator.exchange": {
"total": 0.0249469489999683,
"count": 1,
"is_parallel": true,
"self": 0.0249469489999683
},
"steps_from_proto": {
"total": 0.0007310109999707493,
"count": 1,
"is_parallel": true,
"self": 0.0002396639999915351,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004913469999792142,
"count": 2,
"is_parallel": true,
"self": 0.0004913469999792142
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1165.239434219014,
"count": 233956,
"is_parallel": true,
"self": 33.46578382798043,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 73.88071375097843,
"count": 233956,
"is_parallel": true,
"self": 73.88071375097843
},
"communicator.exchange": {
"total": 966.6561637439845,
"count": 233956,
"is_parallel": true,
"self": 966.6561637439845
},
"steps_from_proto": {
"total": 91.23677289607053,
"count": 233956,
"is_parallel": true,
"self": 37.45640671298463,
"children": {
"_process_rank_one_or_two_observation": {
"total": 53.7803661830859,
"count": 467912,
"is_parallel": true,
"self": 53.7803661830859
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 470.4648487040188,
"count": 233957,
"self": 5.939337190998003,
"children": {
"process_trajectory": {
"total": 151.78811472402128,
"count": 233957,
"self": 150.5956008040215,
"children": {
"RLTrainer._checkpoint": {
"total": 1.192513919999783,
"count": 10,
"self": 1.192513919999783
}
}
},
"_update_policy": {
"total": 312.7373967889995,
"count": 97,
"self": 260.10850436100407,
"children": {
"TorchPPOOptimizer.update": {
"total": 52.628892427995424,
"count": 2910,
"self": 52.628892427995424
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.589998626324814e-07,
"count": 1,
"self": 9.589998626324814e-07
},
"TrainerController._save_models": {
"total": 0.11934349700004532,
"count": 1,
"self": 0.001956787999915832,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11738670900012949,
"count": 1,
"self": 0.11738670900012949
}
}
}
}
}
}
}