ppo-Huggy / run_logs /timers.json
JTStephens's picture
Huggy
d2ec92d
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4045848846435547,
"min": 1.4045848846435547,
"max": 1.4301155805587769,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70348.6328125,
"min": 68204.3828125,
"max": 76720.671875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 133.56368563685638,
"min": 111.96606334841628,
"max": 391.0703125,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49285.0,
"min": 48950.0,
"max": 50175.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999937.0,
"min": 49995.0,
"max": 1999937.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999937.0,
"min": 49995.0,
"max": 1999937.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.216578483581543,
"min": 0.030860163271427155,
"max": 2.3166685104370117,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 817.91748046875,
"min": 3.919240713119507,
"max": 1016.59033203125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.2985830386156634,
"min": 1.8307909322535898,
"max": 3.7626223576981483,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1217.1771412491798,
"min": 232.5104483962059,
"max": 1572.776145517826,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.2985830386156634,
"min": 1.8307909322535898,
"max": 3.7626223576981483,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1217.1771412491798,
"min": 232.5104483962059,
"max": 1572.776145517826,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01494448358619896,
"min": 0.013883988587622298,
"max": 0.01972266140898379,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.02988896717239792,
"min": 0.027767977175244596,
"max": 0.059167984226951374,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.039962173687915006,
"min": 0.02293553501367569,
"max": 0.06684289231068559,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.07992434737583001,
"min": 0.04587107002735138,
"max": 0.20052867693205675,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.399823533424992e-06,
"min": 4.399823533424992e-06,
"max": 0.000295314676561775,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.799647066849985e-06,
"min": 8.799647066849985e-06,
"max": 0.0008437744687418501,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10146657500000003,
"min": 0.10146657500000003,
"max": 0.19843822500000008,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20293315000000006,
"min": 0.20293315000000006,
"max": 0.5812581499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.31820924999999e-05,
"min": 8.31820924999999e-05,
"max": 0.004922067427499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001663641849999998,
"min": 0.0001663641849999998,
"max": 0.014064781685,
"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": "1687719703",
"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 --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": "1687722013"
},
"total": 2309.799974934,
"count": 1,
"self": 0.4358985480002957,
"children": {
"run_training.setup": {
"total": 0.0591288119999831,
"count": 1,
"self": 0.0591288119999831
},
"TrainerController.start_learning": {
"total": 2309.304947574,
"count": 1,
"self": 4.057119017014429,
"children": {
"TrainerController._reset_env": {
"total": 4.805572029000018,
"count": 1,
"self": 4.805572029000018
},
"TrainerController.advance": {
"total": 2300.3271075599855,
"count": 230165,
"self": 4.235485161993438,
"children": {
"env_step": {
"total": 1798.4816398280266,
"count": 230165,
"self": 1516.7445286059897,
"children": {
"SubprocessEnvManager._take_step": {
"total": 279.04136502301236,
"count": 230165,
"self": 16.920141170975683,
"children": {
"TorchPolicy.evaluate": {
"total": 262.1212238520367,
"count": 222940,
"self": 262.1212238520367
}
}
},
"workers": {
"total": 2.695746199024427,
"count": 230165,
"self": 0.0,
"children": {
"worker_root": {
"total": 2301.7801515920005,
"count": 230165,
"is_parallel": true,
"self": 1061.288254957949,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011756869999999253,
"count": 1,
"is_parallel": true,
"self": 0.00035200799999302035,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000823679000006905,
"count": 2,
"is_parallel": true,
"self": 0.000823679000006905
}
}
},
"UnityEnvironment.step": {
"total": 0.027977771999985634,
"count": 1,
"is_parallel": true,
"self": 0.0003364789999977802,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021786500002463072,
"count": 1,
"is_parallel": true,
"self": 0.00021786500002463072
},
"communicator.exchange": {
"total": 0.026699749999977485,
"count": 1,
"is_parallel": true,
"self": 0.026699749999977485
},
"steps_from_proto": {
"total": 0.000723677999985739,
"count": 1,
"is_parallel": true,
"self": 0.0002119179999908738,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005117599999948652,
"count": 2,
"is_parallel": true,
"self": 0.0005117599999948652
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1240.4918966340515,
"count": 230164,
"is_parallel": true,
"self": 38.59762814705073,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 76.36844362099419,
"count": 230164,
"is_parallel": true,
"self": 76.36844362099419
},
"communicator.exchange": {
"total": 1033.442938414905,
"count": 230164,
"is_parallel": true,
"self": 1033.442938414905
},
"steps_from_proto": {
"total": 92.0828864511015,
"count": 230164,
"is_parallel": true,
"self": 32.6668446730655,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.416041778036,
"count": 460328,
"is_parallel": true,
"self": 59.416041778036
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 497.6099825699657,
"count": 230165,
"self": 6.620586498017531,
"children": {
"process_trajectory": {
"total": 121.96634097994837,
"count": 230165,
"self": 120.66364002994811,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3027009500002578,
"count": 10,
"self": 1.3027009500002578
}
}
},
"_update_policy": {
"total": 369.0230550919998,
"count": 96,
"self": 310.2114459190099,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.811609172989904,
"count": 2880,
"self": 58.811609172989904
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.049999789567664e-07,
"count": 1,
"self": 9.049999789567664e-07
},
"TrainerController._save_models": {
"total": 0.11514806300010605,
"count": 1,
"self": 0.0021440330001496477,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1130040299999564,
"count": 1,
"self": 0.1130040299999564
}
}
}
}
}
}
}