ppo-Huggy / run_logs /timers.json
zpattdev's picture
Huggy first
2ecd642
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4037833213806152,
"min": 1.4037833213806152,
"max": 1.4303478002548218,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70093.7109375,
"min": 67803.5625,
"max": 77742.90625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 108.85054945054945,
"min": 98.93158953722335,
"max": 419.06666666666666,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49527.0,
"min": 49169.0,
"max": 50288.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999999.0,
"min": 49896.0,
"max": 1999999.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999999.0,
"min": 49896.0,
"max": 1999999.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.24501371383667,
"min": 0.1360444277524948,
"max": 2.3905246257781982,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1021.481201171875,
"min": 16.189287185668945,
"max": 1145.061279296875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.4104085738842302,
"min": 1.9488040426699054,
"max": 3.8002376397118938,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1551.7359011173248,
"min": 231.90768107771873,
"max": 1820.313829421997,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.4104085738842302,
"min": 1.9488040426699054,
"max": 3.8002376397118938,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1551.7359011173248,
"min": 231.90768107771873,
"max": 1820.313829421997,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016346424333945227,
"min": 0.014390605752649005,
"max": 0.019193901694355496,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.032692848667890455,
"min": 0.02925792441237718,
"max": 0.05746744306137164,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04562561220179001,
"min": 0.020743385857592028,
"max": 0.06444381730010112,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.09125122440358002,
"min": 0.041486771715184056,
"max": 0.190119756385684,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.899198700299995e-06,
"min": 3.899198700299995e-06,
"max": 0.000295281076572975,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 7.79839740059999e-06,
"min": 7.79839740059999e-06,
"max": 0.0008439168186944,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1012997,
"min": 0.1012997,
"max": 0.19842702499999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.2025994,
"min": 0.2025994,
"max": 0.5813056000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.485502999999992e-05,
"min": 7.485502999999992e-05,
"max": 0.0049215085475,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00014971005999999984,
"min": 0.00014971005999999984,
"max": 0.014067149440000003,
"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": "1685893107",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1685895765"
},
"total": 2657.403951786,
"count": 1,
"self": 0.439061849999689,
"children": {
"run_training.setup": {
"total": 0.0406363600000077,
"count": 1,
"self": 0.0406363600000077
},
"TrainerController.start_learning": {
"total": 2656.9242535760004,
"count": 1,
"self": 5.28881431110176,
"children": {
"TrainerController._reset_env": {
"total": 3.825681578000058,
"count": 1,
"self": 3.825681578000058
},
"TrainerController.advance": {
"total": 2647.686320925899,
"count": 230967,
"self": 5.198007300645713,
"children": {
"env_step": {
"total": 2101.2150940191495,
"count": 230967,
"self": 1772.8158175760864,
"children": {
"SubprocessEnvManager._take_step": {
"total": 325.1498776161184,
"count": 230967,
"self": 19.09371218513138,
"children": {
"TorchPolicy.evaluate": {
"total": 306.056165430987,
"count": 223012,
"self": 306.056165430987
}
}
},
"workers": {
"total": 3.249398826944798,
"count": 230967,
"self": 0.0,
"children": {
"worker_root": {
"total": 2648.1134144831917,
"count": 230967,
"is_parallel": true,
"self": 1203.4017204861545,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010431949999656354,
"count": 1,
"is_parallel": true,
"self": 0.0002898509999340604,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000753344000031575,
"count": 2,
"is_parallel": true,
"self": 0.000753344000031575
}
}
},
"UnityEnvironment.step": {
"total": 0.03265237200002957,
"count": 1,
"is_parallel": true,
"self": 0.0003580380000585137,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00024522200010324013,
"count": 1,
"is_parallel": true,
"self": 0.00024522200010324013
},
"communicator.exchange": {
"total": 0.031229715999870677,
"count": 1,
"is_parallel": true,
"self": 0.031229715999870677
},
"steps_from_proto": {
"total": 0.0008193959999971412,
"count": 1,
"is_parallel": true,
"self": 0.0002516020001621655,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005677939998349757,
"count": 2,
"is_parallel": true,
"self": 0.0005677939998349757
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1444.7116939970372,
"count": 230966,
"is_parallel": true,
"self": 42.91869623732782,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 88.03921581680652,
"count": 230966,
"is_parallel": true,
"self": 88.03921581680652
},
"communicator.exchange": {
"total": 1207.3075217050302,
"count": 230966,
"is_parallel": true,
"self": 1207.3075217050302
},
"steps_from_proto": {
"total": 106.4462602378726,
"count": 230966,
"is_parallel": true,
"self": 39.644181006747885,
"children": {
"_process_rank_one_or_two_observation": {
"total": 66.80207923112471,
"count": 461932,
"is_parallel": true,
"self": 66.80207923112471
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 541.2732196061038,
"count": 230967,
"self": 8.076201273118386,
"children": {
"process_trajectory": {
"total": 141.74340805898214,
"count": 230967,
"self": 140.40859102398213,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3348170350000146,
"count": 10,
"self": 1.3348170350000146
}
}
},
"_update_policy": {
"total": 391.45361027400327,
"count": 96,
"self": 331.7433274280029,
"children": {
"TorchPPOOptimizer.update": {
"total": 59.71028284600038,
"count": 2880,
"self": 59.71028284600038
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.05399976746412e-06,
"count": 1,
"self": 1.05399976746412e-06
},
"TrainerController._save_models": {
"total": 0.12343570699977136,
"count": 1,
"self": 0.0028049539996573003,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12063075300011405,
"count": 1,
"self": 0.12063075300011405
}
}
}
}
}
}
}