ppo-Huggy / run_logs /timers.json
robinsk8a's picture
First commit Huggy
78997b8
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4075833559036255,
"min": 1.4075833559036255,
"max": 1.425537347793579,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70493.1796875,
"min": 68815.2421875,
"max": 75696.75,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 90.53663003663004,
"min": 85.05335628227195,
"max": 413.27272727272725,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49433.0,
"min": 49282.0,
"max": 50006.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999972.0,
"min": 49688.0,
"max": 1999972.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999972.0,
"min": 49688.0,
"max": 1999972.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4347896575927734,
"min": -0.002871578326448798,
"max": 2.4420928955078125,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1329.3951416015625,
"min": -0.3445894122123718,
"max": 1392.3221435546875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.787683965413125,
"min": 1.8942331480483214,
"max": 4.021934248564779,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2068.0754451155663,
"min": 227.30797776579857,
"max": 2160.9920114278793,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.787683965413125,
"min": 1.8942331480483214,
"max": 4.021934248564779,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2068.0754451155663,
"min": 227.30797776579857,
"max": 2160.9920114278793,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01512625815133409,
"min": 0.013449151267074437,
"max": 0.02061832764496406,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04537877445400227,
"min": 0.026898302534148873,
"max": 0.06185498293489218,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.056236341802610286,
"min": 0.023690617891649404,
"max": 0.058399521890613766,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16870902540783086,
"min": 0.04738123578329881,
"max": 0.1751985656718413,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.6755987748333314e-06,
"min": 3.6755987748333314e-06,
"max": 0.0002953669515443499,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1026796324499994e-05,
"min": 1.1026796324499994e-05,
"max": 0.0008442897185700998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10122516666666669,
"min": 0.10122516666666669,
"max": 0.19845564999999993,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30367550000000004,
"min": 0.20759500000000003,
"max": 0.5814298999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.113581666666664e-05,
"min": 7.113581666666664e-05,
"max": 0.004922936935,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021340744999999992,
"min": 0.00021340744999999992,
"max": 0.014073352010000002,
"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": "1674829722",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[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": "0.29.0.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": "1674831898"
},
"total": 2176.321086449,
"count": 1,
"self": 0.39997410400064837,
"children": {
"run_training.setup": {
"total": 0.11708238100004564,
"count": 1,
"self": 0.11708238100004564
},
"TrainerController.start_learning": {
"total": 2175.8040299639997,
"count": 1,
"self": 3.7149483729108397,
"children": {
"TrainerController._reset_env": {
"total": 9.853130316000033,
"count": 1,
"self": 9.853130316000033
},
"TrainerController.advance": {
"total": 2162.1278882910888,
"count": 232036,
"self": 4.073065724051048,
"children": {
"env_step": {
"total": 1702.2373215790717,
"count": 232036,
"self": 1432.9892432601243,
"children": {
"SubprocessEnvManager._take_step": {
"total": 266.6988642699571,
"count": 232036,
"self": 14.18638586489908,
"children": {
"TorchPolicy.evaluate": {
"total": 252.512478405058,
"count": 222918,
"self": 63.22870069005228,
"children": {
"TorchPolicy.sample_actions": {
"total": 189.28377771500573,
"count": 222918,
"self": 189.28377771500573
}
}
}
}
},
"workers": {
"total": 2.5492140489902795,
"count": 232036,
"self": 0.0,
"children": {
"worker_root": {
"total": 2168.2460312280077,
"count": 232036,
"is_parallel": true,
"self": 984.1106294780452,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0016030049999926632,
"count": 1,
"is_parallel": true,
"self": 0.00030098499996711325,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00130202000002555,
"count": 2,
"is_parallel": true,
"self": 0.00130202000002555
}
}
},
"UnityEnvironment.step": {
"total": 0.027687726999943152,
"count": 1,
"is_parallel": true,
"self": 0.0002737740001066413,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002188849999811282,
"count": 1,
"is_parallel": true,
"self": 0.0002188849999811282
},
"communicator.exchange": {
"total": 0.026353241999913735,
"count": 1,
"is_parallel": true,
"self": 0.026353241999913735
},
"steps_from_proto": {
"total": 0.0008418259999416478,
"count": 1,
"is_parallel": true,
"self": 0.00022446999980729743,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006173560001343503,
"count": 2,
"is_parallel": true,
"self": 0.0006173560001343503
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1184.1354017499625,
"count": 232035,
"is_parallel": true,
"self": 33.67592749485539,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 72.99204134506431,
"count": 232035,
"is_parallel": true,
"self": 72.99204134506431
},
"communicator.exchange": {
"total": 988.2482826360128,
"count": 232035,
"is_parallel": true,
"self": 988.2482826360128
},
"steps_from_proto": {
"total": 89.21915027402997,
"count": 232035,
"is_parallel": true,
"self": 36.75653386884824,
"children": {
"_process_rank_one_or_two_observation": {
"total": 52.462616405181734,
"count": 464070,
"is_parallel": true,
"self": 52.462616405181734
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 455.8175009879661,
"count": 232036,
"self": 6.121527138906686,
"children": {
"process_trajectory": {
"total": 143.80953085605825,
"count": 232036,
"self": 142.72985888905782,
"children": {
"RLTrainer._checkpoint": {
"total": 1.0796719670004222,
"count": 10,
"self": 1.0796719670004222
}
}
},
"_update_policy": {
"total": 305.8864429930012,
"count": 97,
"self": 252.59477752699547,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.291665466005725,
"count": 2910,
"self": 53.291665466005725
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.689997568784747e-07,
"count": 1,
"self": 9.689997568784747e-07
},
"TrainerController._save_models": {
"total": 0.10806201500008683,
"count": 1,
"self": 0.00291867900023135,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10514333599985548,
"count": 1,
"self": 0.10514333599985548
}
}
}
}
}
}
}