ppo-Huggy / run_logs /timers.json
jonv1's picture
Huggy
2e93d47 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4046621322631836,
"min": 1.4046621322631836,
"max": 1.4252654314041138,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69546.2265625,
"min": 67580.046875,
"max": 76203.5625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 103.88469601677149,
"min": 82.77721943048576,
"max": 377.969696969697,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49553.0,
"min": 48922.0,
"max": 49965.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999977.0,
"min": 49737.0,
"max": 1999977.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999977.0,
"min": 49737.0,
"max": 1999977.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.371934413909912,
"min": 0.15806905925273895,
"max": 2.50203800201416,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1131.4127197265625,
"min": 20.707046508789062,
"max": 1463.7752685546875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.645506493575418,
"min": 1.9002143137782586,
"max": 3.982404008750024,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1738.9065974354744,
"min": 248.92807510495186,
"max": 2293.1219632029533,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.645506493575418,
"min": 1.9002143137782586,
"max": 3.982404008750024,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1738.9065974354744,
"min": 248.92807510495186,
"max": 2293.1219632029533,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01890501865911776,
"min": 0.010810421974747443,
"max": 0.02097244942706311,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05671505597735328,
"min": 0.021620843949494886,
"max": 0.05676048254730025,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0498679203291734,
"min": 0.02171915282184879,
"max": 0.059903483962019284,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1496037609875202,
"min": 0.04343830564369758,
"max": 0.17124876814583936,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.6467487844499953e-06,
"min": 3.6467487844499953e-06,
"max": 0.0002953815015395,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0940246353349985e-05,
"min": 1.0940246353349985e-05,
"max": 0.00084418366860545,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10121555,
"min": 0.10121555,
"max": 0.19846049999999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30364665,
"min": 0.20756684999999997,
"max": 0.5813945499999998,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.065594499999996e-05,
"min": 7.065594499999996e-05,
"max": 0.004923178950000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021196783499999986,
"min": 0.00021196783499999986,
"max": 0.014071588044999996,
"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": "1734909009",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1734911728"
},
"total": 2719.8031285720003,
"count": 1,
"self": 0.49070759000005637,
"children": {
"run_training.setup": {
"total": 0.05896362900011809,
"count": 1,
"self": 0.05896362900011809
},
"TrainerController.start_learning": {
"total": 2719.253457353,
"count": 1,
"self": 5.484846362959615,
"children": {
"TrainerController._reset_env": {
"total": 4.97237984100002,
"count": 1,
"self": 4.97237984100002
},
"TrainerController.advance": {
"total": 2708.66278435904,
"count": 232008,
"self": 5.438985616110131,
"children": {
"env_step": {
"total": 2194.8655488520526,
"count": 232008,
"self": 1726.0541927472466,
"children": {
"SubprocessEnvManager._take_step": {
"total": 465.3647847659497,
"count": 232008,
"self": 17.707428902886704,
"children": {
"TorchPolicy.evaluate": {
"total": 447.657355863063,
"count": 222968,
"self": 447.657355863063
}
}
},
"workers": {
"total": 3.4465713388563017,
"count": 232008,
"self": 0.0,
"children": {
"worker_root": {
"total": 2711.1522803860325,
"count": 232008,
"is_parallel": true,
"self": 1314.2607784080983,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008863939999628201,
"count": 1,
"is_parallel": true,
"self": 0.0002689949999421515,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006173990000206686,
"count": 2,
"is_parallel": true,
"self": 0.0006173990000206686
}
}
},
"UnityEnvironment.step": {
"total": 0.03382534599995779,
"count": 1,
"is_parallel": true,
"self": 0.00038989799986666185,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002271020000534918,
"count": 1,
"is_parallel": true,
"self": 0.0002271020000534918
},
"communicator.exchange": {
"total": 0.03240198200001032,
"count": 1,
"is_parallel": true,
"self": 0.03240198200001032
},
"steps_from_proto": {
"total": 0.0008063640000273153,
"count": 1,
"is_parallel": true,
"self": 0.00024869799995030917,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005576660000770062,
"count": 2,
"is_parallel": true,
"self": 0.0005576660000770062
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1396.8915019779342,
"count": 232007,
"is_parallel": true,
"self": 41.39482091915988,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 89.40381853496001,
"count": 232007,
"is_parallel": true,
"self": 89.40381853496001
},
"communicator.exchange": {
"total": 1167.2639930308435,
"count": 232007,
"is_parallel": true,
"self": 1167.2639930308435
},
"steps_from_proto": {
"total": 98.82886949297085,
"count": 232007,
"is_parallel": true,
"self": 37.01139421491325,
"children": {
"_process_rank_one_or_two_observation": {
"total": 61.8174752780576,
"count": 464014,
"is_parallel": true,
"self": 61.8174752780576
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 508.358249890877,
"count": 232008,
"self": 7.8695062329447865,
"children": {
"process_trajectory": {
"total": 187.11277445393534,
"count": 232008,
"self": 185.59916731893532,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5136071350000293,
"count": 10,
"self": 1.5136071350000293
}
}
},
"_update_policy": {
"total": 313.3759692039969,
"count": 97,
"self": 248.02553123700886,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.35043796698801,
"count": 2910,
"self": 65.35043796698801
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1700003597070463e-06,
"count": 1,
"self": 1.1700003597070463e-06
},
"TrainerController._save_models": {
"total": 0.13344562000020233,
"count": 1,
"self": 0.003635080999629281,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12981053900057304,
"count": 1,
"self": 0.12981053900057304
}
}
}
}
}
}
}