ppo-Huggy / run_logs /timers.json
vind's picture
Huggy
99aa9ab
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4072884321212769,
"min": 1.4072884321212769,
"max": 1.4287470579147339,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70282.796875,
"min": 69275.0546875,
"max": 77603.6015625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 90.3491773308958,
"min": 84.7409948542024,
"max": 393.4765625,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49421.0,
"min": 48909.0,
"max": 50365.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999998.0,
"min": 49928.0,
"max": 1999998.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999998.0,
"min": 49928.0,
"max": 1999998.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.405818223953247,
"min": 0.06395981460809708,
"max": 2.452899694442749,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1318.388427734375,
"min": 8.122896194458008,
"max": 1412.404296875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7225990311725297,
"min": 1.8627399579277188,
"max": 3.957802205881364,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2039.9842690825462,
"min": 236.5679746568203,
"max": 2235.251387298107,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7225990311725297,
"min": 1.8627399579277188,
"max": 3.957802205881364,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2039.9842690825462,
"min": 236.5679746568203,
"max": 2235.251387298107,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017819236943291294,
"min": 0.011879285939115409,
"max": 0.019387619673701312,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05345771082987388,
"min": 0.02878761385315253,
"max": 0.05592638253195521,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05409215605921216,
"min": 0.023339732798437277,
"max": 0.05988867102811734,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16227646817763647,
"min": 0.04667946559687455,
"max": 0.16956765117744604,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5186488271500107e-06,
"min": 3.5186488271500107e-06,
"max": 0.00029532082655972503,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0555946481450032e-05,
"min": 1.0555946481450032e-05,
"max": 0.0008440344186551997,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10117285,
"min": 0.10117285,
"max": 0.19844027499999997,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30351855,
"min": 0.20751180000000005,
"max": 0.5813448,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.852521500000017e-05,
"min": 6.852521500000017e-05,
"max": 0.004922169722500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002055756450000005,
"min": 0.0002055756450000005,
"max": 0.014069105520000003,
"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": "1684218481",
"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": "1684221063"
},
"total": 2582.3086058850004,
"count": 1,
"self": 0.44211972700031765,
"children": {
"run_training.setup": {
"total": 0.05462044900002638,
"count": 1,
"self": 0.05462044900002638
},
"TrainerController.start_learning": {
"total": 2581.811865709,
"count": 1,
"self": 4.848818186021617,
"children": {
"TrainerController._reset_env": {
"total": 3.8783360479999374,
"count": 1,
"self": 3.8783360479999374
},
"TrainerController.advance": {
"total": 2572.959933123978,
"count": 231960,
"self": 4.908329589000914,
"children": {
"env_step": {
"total": 2026.1205850900158,
"count": 231960,
"self": 1707.505772734948,
"children": {
"SubprocessEnvManager._take_step": {
"total": 315.4414301509247,
"count": 231960,
"self": 18.23603570596879,
"children": {
"TorchPolicy.evaluate": {
"total": 297.2053944449559,
"count": 222889,
"self": 297.2053944449559
}
}
},
"workers": {
"total": 3.173382204142854,
"count": 231960,
"self": 0.0,
"children": {
"worker_root": {
"total": 2573.3406938400226,
"count": 231960,
"is_parallel": true,
"self": 1181.7512586331572,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010229759999447197,
"count": 1,
"is_parallel": true,
"self": 0.00032349499997508246,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006994809999696372,
"count": 2,
"is_parallel": true,
"self": 0.0006994809999696372
}
}
},
"UnityEnvironment.step": {
"total": 0.03538987400008864,
"count": 1,
"is_parallel": true,
"self": 0.00037316500015549536,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00025727799993546796,
"count": 1,
"is_parallel": true,
"self": 0.00025727799993546796
},
"communicator.exchange": {
"total": 0.033927197000025444,
"count": 1,
"is_parallel": true,
"self": 0.033927197000025444
},
"steps_from_proto": {
"total": 0.0008322339999722317,
"count": 1,
"is_parallel": true,
"self": 0.0002559050000172647,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000576328999954967,
"count": 2,
"is_parallel": true,
"self": 0.000576328999954967
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1391.5894352068653,
"count": 231959,
"is_parallel": true,
"self": 40.39631037676145,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 85.5772725290966,
"count": 231959,
"is_parallel": true,
"self": 85.5772725290966
},
"communicator.exchange": {
"total": 1165.7694436040604,
"count": 231959,
"is_parallel": true,
"self": 1165.7694436040604
},
"steps_from_proto": {
"total": 99.84640869694704,
"count": 231959,
"is_parallel": true,
"self": 38.77569188695827,
"children": {
"_process_rank_one_or_two_observation": {
"total": 61.07071680998877,
"count": 463918,
"is_parallel": true,
"self": 61.07071680998877
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 541.9310184449613,
"count": 231960,
"self": 7.293835478984988,
"children": {
"process_trajectory": {
"total": 145.91867759097647,
"count": 231960,
"self": 144.46751316297616,
"children": {
"RLTrainer._checkpoint": {
"total": 1.451164428000311,
"count": 10,
"self": 1.451164428000311
}
}
},
"_update_policy": {
"total": 388.71850537499984,
"count": 97,
"self": 327.45613025799685,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.26237511700299,
"count": 2910,
"self": 61.26237511700299
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.76000137598021e-07,
"count": 1,
"self": 9.76000137598021e-07
},
"TrainerController._save_models": {
"total": 0.12477737500012154,
"count": 1,
"self": 0.0021717050003644545,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12260566999975708,
"count": 1,
"self": 0.12260566999975708
}
}
}
}
}
}
}