ppo-Huggy-pdx / run_logs /timers.json
pdx97's picture
Huggy
ab4d086 verified
raw
history blame
17.5 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4149426221847534,
"min": 1.4149426221847534,
"max": 1.4331305027008057,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71830.9765625,
"min": 68089.6328125,
"max": 77475.328125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 79.35702746365105,
"min": 79.35702746365105,
"max": 410.130081300813,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49122.0,
"min": 49122.0,
"max": 50446.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999950.0,
"min": 49963.0,
"max": 1999950.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999950.0,
"min": 49963.0,
"max": 1999950.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.449042320251465,
"min": 0.06342756003141403,
"max": 2.5164341926574707,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1515.9571533203125,
"min": 7.738162517547607,
"max": 1520.100341796875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7696160646170522,
"min": 1.8293354672486666,
"max": 3.9673868162003725,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2333.3923439979553,
"min": 223.1789270043373,
"max": 2351.962267100811,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7696160646170522,
"min": 1.8293354672486666,
"max": 3.9673868162003725,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2333.3923439979553,
"min": 223.1789270043373,
"max": 2351.962267100811,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01853031347078892,
"min": 0.013399877319655692,
"max": 0.020681353988927894,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.055590940412366764,
"min": 0.026799754639311384,
"max": 0.06204406196678368,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05742749720811844,
"min": 0.02214853335171938,
"max": 0.06619874508016639,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17228249162435533,
"min": 0.04429706670343876,
"max": 0.19859623524049919,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.3573988808999954e-06,
"min": 3.3573988808999954e-06,
"max": 0.00029529570156809994,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0072196642699987e-05,
"min": 1.0072196642699987e-05,
"max": 0.0008438910187029997,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10111910000000002,
"min": 0.10111910000000002,
"max": 0.19843189999999997,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30335730000000005,
"min": 0.20738465000000006,
"max": 0.581297,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.584308999999995e-05,
"min": 6.584308999999995e-05,
"max": 0.00492175181,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019752926999999984,
"min": 0.00019752926999999984,
"max": 0.014066720299999998,
"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": "1710518393",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1710521195"
},
"total": 2802.1356530740004,
"count": 1,
"self": 0.43593127100075435,
"children": {
"run_training.setup": {
"total": 0.05685916799984625,
"count": 1,
"self": 0.05685916799984625
},
"TrainerController.start_learning": {
"total": 2801.642862635,
"count": 1,
"self": 5.5982294811169595,
"children": {
"TrainerController._reset_env": {
"total": 2.8701727719999326,
"count": 1,
"self": 2.8701727719999326
},
"TrainerController.advance": {
"total": 2793.084690985883,
"count": 232491,
"self": 5.4562668060243595,
"children": {
"env_step": {
"total": 1798.4076865437964,
"count": 232491,
"self": 1502.2584637206685,
"children": {
"SubprocessEnvManager._take_step": {
"total": 292.6800044831218,
"count": 232491,
"self": 16.264137340164552,
"children": {
"TorchPolicy.evaluate": {
"total": 276.41586714295727,
"count": 222939,
"self": 276.41586714295727
}
}
},
"workers": {
"total": 3.4692183400061367,
"count": 232491,
"self": 0.0,
"children": {
"worker_root": {
"total": 2793.3532927589663,
"count": 232491,
"is_parallel": true,
"self": 1599.4529984799462,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0006252600001062092,
"count": 1,
"is_parallel": true,
"self": 0.00015903000007710943,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00046623000002909976,
"count": 2,
"is_parallel": true,
"self": 0.00046623000002909976
}
}
},
"UnityEnvironment.step": {
"total": 0.030778778000012608,
"count": 1,
"is_parallel": true,
"self": 0.00037760899999739195,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00016062999998212035,
"count": 1,
"is_parallel": true,
"self": 0.00016062999998212035
},
"communicator.exchange": {
"total": 0.029414508999934696,
"count": 1,
"is_parallel": true,
"self": 0.029414508999934696
},
"steps_from_proto": {
"total": 0.0008260300000983989,
"count": 1,
"is_parallel": true,
"self": 0.00020526000002973888,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00062077000006866,
"count": 2,
"is_parallel": true,
"self": 0.00062077000006866
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1193.90029427902,
"count": 232490,
"is_parallel": true,
"self": 39.31093646009003,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 60.53119077293377,
"count": 232490,
"is_parallel": true,
"self": 60.53119077293377
},
"communicator.exchange": {
"total": 1006.8966018219489,
"count": 232490,
"is_parallel": true,
"self": 1006.8966018219489
},
"steps_from_proto": {
"total": 87.16156522404731,
"count": 232490,
"is_parallel": true,
"self": 31.574336780194244,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.587228443853064,
"count": 464980,
"is_parallel": true,
"self": 55.587228443853064
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 989.2207376360623,
"count": 232491,
"self": 8.806885317090064,
"children": {
"process_trajectory": {
"total": 168.40710058697277,
"count": 232491,
"self": 167.58643686997243,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8206637170003432,
"count": 10,
"self": 0.8206637170003432
}
}
},
"_update_policy": {
"total": 812.0067517319994,
"count": 97,
"self": 207.6221170720073,
"children": {
"TorchPPOOptimizer.update": {
"total": 604.3846346599921,
"count": 2910,
"self": 604.3846346599921
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.700000423938036e-07,
"count": 1,
"self": 7.700000423938036e-07
},
"TrainerController._save_models": {
"total": 0.08976862600002278,
"count": 1,
"self": 0.0039870699997663905,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08578155600025639,
"count": 1,
"self": 0.08578155600025639
}
}
}
}
}
}
}