ppo-Huggy / run_logs /timers.json
zhundred's picture
Huggy
a7447e7
raw
history blame
17.5 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4024590253829956,
"min": 1.4024478197097778,
"max": 1.4279943704605103,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71913.890625,
"min": 68503.8359375,
"max": 75788.6640625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 79.74151857835218,
"min": 79.74151857835218,
"max": 397.26190476190476,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49360.0,
"min": 49048.0,
"max": 50055.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999995.0,
"min": 49431.0,
"max": 1999995.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999995.0,
"min": 49431.0,
"max": 1999995.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4601597785949707,
"min": -0.012445439584553242,
"max": 2.4669981002807617,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1522.8388671875,
"min": -1.5556799173355103,
"max": 1522.8388671875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7941289315893885,
"min": 1.808132660627365,
"max": 3.927234430698185,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2348.5658086538315,
"min": 226.01658257842064,
"max": 2348.5658086538315,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7941289315893885,
"min": 1.808132660627365,
"max": 3.927234430698185,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2348.5658086538315,
"min": 226.01658257842064,
"max": 2348.5658086538315,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017476627082538068,
"min": 0.013442644705840697,
"max": 0.02054801555738474,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.052429881247614205,
"min": 0.026885289411681394,
"max": 0.057643895538058126,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06094447295698855,
"min": 0.023354822800805173,
"max": 0.06438300559918086,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18283341887096566,
"min": 0.046709645601610346,
"max": 0.18283341887096566,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.350748883116666e-06,
"min": 3.350748883116666e-06,
"max": 0.00029528602657132497,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0052246649349998e-05,
"min": 1.0052246649349998e-05,
"max": 0.0008438889187036998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10111688333333335,
"min": 0.10111688333333335,
"max": 0.19842867500000005,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30335065000000005,
"min": 0.20736494999999994,
"max": 0.5812963000000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.573247833333334e-05,
"min": 6.573247833333334e-05,
"max": 0.004921590882500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.000197197435,
"min": 0.000197197435,
"max": 0.01406668537,
"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": "1688626882",
"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.x86_64 --run-id=Huggy --no-graphics --force",
"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": "1688629223"
},
"total": 2340.9608743420004,
"count": 1,
"self": 0.43720340700019733,
"children": {
"run_training.setup": {
"total": 0.061460698000018965,
"count": 1,
"self": 0.061460698000018965
},
"TrainerController.start_learning": {
"total": 2340.4622102370004,
"count": 1,
"self": 4.202008816989746,
"children": {
"TrainerController._reset_env": {
"total": 4.286190506999901,
"count": 1,
"self": 4.286190506999901
},
"TrainerController.advance": {
"total": 2331.842387898011,
"count": 232522,
"self": 4.415168768066906,
"children": {
"env_step": {
"total": 1815.348270567975,
"count": 232522,
"self": 1527.176965796915,
"children": {
"SubprocessEnvManager._take_step": {
"total": 285.4515822260587,
"count": 232522,
"self": 16.298138787913558,
"children": {
"TorchPolicy.evaluate": {
"total": 269.15344343814513,
"count": 223030,
"self": 269.15344343814513
}
}
},
"workers": {
"total": 2.719722545001332,
"count": 232522,
"self": 0.0,
"children": {
"worker_root": {
"total": 2333.023141235085,
"count": 232522,
"is_parallel": true,
"self": 1087.2630291610437,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010873349999656057,
"count": 1,
"is_parallel": true,
"self": 0.0002680359998521453,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008192990001134604,
"count": 2,
"is_parallel": true,
"self": 0.0008192990001134604
}
}
},
"UnityEnvironment.step": {
"total": 0.028124442000034833,
"count": 1,
"is_parallel": true,
"self": 0.0002987899999880028,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002152079998722911,
"count": 1,
"is_parallel": true,
"self": 0.0002152079998722911
},
"communicator.exchange": {
"total": 0.026904471000079866,
"count": 1,
"is_parallel": true,
"self": 0.026904471000079866
},
"steps_from_proto": {
"total": 0.0007059730000946729,
"count": 1,
"is_parallel": true,
"self": 0.00020282700006646337,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005031460000282095,
"count": 2,
"is_parallel": true,
"self": 0.0005031460000282095
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1245.7601120740412,
"count": 232521,
"is_parallel": true,
"self": 37.811718143949975,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 76.94411539404769,
"count": 232521,
"is_parallel": true,
"self": 76.94411539404769
},
"communicator.exchange": {
"total": 1038.9090933469554,
"count": 232521,
"is_parallel": true,
"self": 1038.9090933469554
},
"steps_from_proto": {
"total": 92.09518518908817,
"count": 232521,
"is_parallel": true,
"self": 32.77359188520677,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.3215933038814,
"count": 465042,
"is_parallel": true,
"self": 59.3215933038814
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 512.0789485619689,
"count": 232522,
"self": 6.270870103824109,
"children": {
"process_trajectory": {
"total": 131.91567950914282,
"count": 232522,
"self": 130.53717820514316,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3785013039996556,
"count": 10,
"self": 1.3785013039996556
}
}
},
"_update_policy": {
"total": 373.892398949002,
"count": 97,
"self": 313.6246738389873,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.26772511001468,
"count": 2910,
"self": 60.26772511001468
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.171999883808894e-06,
"count": 1,
"self": 1.171999883808894e-06
},
"TrainerController._save_models": {
"total": 0.13162184299972068,
"count": 1,
"self": 0.0023187110000435496,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12930313199967713,
"count": 1,
"self": 0.12930313199967713
}
}
}
}
}
}
}