ppo-Huggy / run_logs /timers.json
RealityAdmin's picture
First time withHuggy
4d52c1e verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4007434844970703,
"min": 1.4007434844970703,
"max": 1.4270167350769043,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70663.3046875,
"min": 69334.7890625,
"max": 77449.1015625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 98.986,
"min": 74.10375939849624,
"max": 377.1278195488722,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49493.0,
"min": 48756.0,
"max": 50158.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999992.0,
"min": 49601.0,
"max": 1999992.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999992.0,
"min": 49601.0,
"max": 1999992.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.435229539871216,
"min": 0.06992587447166443,
"max": 2.502751111984253,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1217.61474609375,
"min": 9.230215072631836,
"max": 1638.32958984375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6380557131767275,
"min": 1.7314980867685694,
"max": 4.011134126046408,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1819.0278565883636,
"min": 228.55774745345116,
"max": 2588.269243299961,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6380557131767275,
"min": 1.7314980867685694,
"max": 4.011134126046408,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1819.0278565883636,
"min": 228.55774745345116,
"max": 2588.269243299961,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014557714056637553,
"min": 0.013595380839251447,
"max": 0.021481524185219314,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04367314216991266,
"min": 0.027190761678502894,
"max": 0.06284987203107448,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.048110630176961426,
"min": 0.0233568319119513,
"max": 0.06562468440582356,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14433189053088427,
"min": 0.0467136638239026,
"max": 0.18318645531932515,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.7033987655666642e-06,
"min": 3.7033987655666642e-06,
"max": 0.00029533912655362493,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1110196296699993e-05,
"min": 1.1110196296699993e-05,
"max": 0.0008439670686776499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10123443333333333,
"min": 0.10123443333333333,
"max": 0.198446375,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3037033,
"min": 0.20762520000000007,
"max": 0.58132235,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.159822333333331e-05,
"min": 7.159822333333331e-05,
"max": 0.004922474112500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021479466999999993,
"min": 0.00021479466999999993,
"max": 0.014067985265000003,
"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": "1733082533",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1733085184"
},
"total": 2651.259611656,
"count": 1,
"self": 0.42700091399956364,
"children": {
"run_training.setup": {
"total": 0.0670819299998584,
"count": 1,
"self": 0.0670819299998584
},
"TrainerController.start_learning": {
"total": 2650.7655288120004,
"count": 1,
"self": 5.0208837521104215,
"children": {
"TrainerController._reset_env": {
"total": 5.0086181449999,
"count": 1,
"self": 5.0086181449999
},
"TrainerController.advance": {
"total": 2640.6093368258903,
"count": 233172,
"self": 4.996103765814496,
"children": {
"env_step": {
"total": 2070.6552163609645,
"count": 233172,
"self": 1628.2211976750846,
"children": {
"SubprocessEnvManager._take_step": {
"total": 439.35468533996277,
"count": 233172,
"self": 17.022137909052162,
"children": {
"TorchPolicy.evaluate": {
"total": 422.3325474309106,
"count": 223098,
"self": 422.3325474309106
}
}
},
"workers": {
"total": 3.079333345917121,
"count": 233172,
"self": 0.0,
"children": {
"worker_root": {
"total": 2642.8571276751504,
"count": 233172,
"is_parallel": true,
"self": 1318.612738757067,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008463130000109231,
"count": 1,
"is_parallel": true,
"self": 0.0002456839999922522,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006006290000186709,
"count": 2,
"is_parallel": true,
"self": 0.0006006290000186709
}
}
},
"UnityEnvironment.step": {
"total": 0.029755905999991228,
"count": 1,
"is_parallel": true,
"self": 0.0004253409997545532,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002295190001859737,
"count": 1,
"is_parallel": true,
"self": 0.0002295190001859737
},
"communicator.exchange": {
"total": 0.02834435900012977,
"count": 1,
"is_parallel": true,
"self": 0.02834435900012977
},
"steps_from_proto": {
"total": 0.0007566869999209302,
"count": 1,
"is_parallel": true,
"self": 0.00020734099985020293,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005493460000707273,
"count": 2,
"is_parallel": true,
"self": 0.0005493460000707273
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1324.2443889180834,
"count": 233171,
"is_parallel": true,
"self": 40.140464710903416,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 88.79068060917257,
"count": 233171,
"is_parallel": true,
"self": 88.79068060917257
},
"communicator.exchange": {
"total": 1099.760216949933,
"count": 233171,
"is_parallel": true,
"self": 1099.760216949933
},
"steps_from_proto": {
"total": 95.55302664807436,
"count": 233171,
"is_parallel": true,
"self": 35.74989969000035,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.80312695807402,
"count": 466342,
"is_parallel": true,
"self": 59.80312695807402
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 564.9580166991111,
"count": 233172,
"self": 7.37622309994822,
"children": {
"process_trajectory": {
"total": 180.12612827216276,
"count": 233172,
"self": 178.44794834416234,
"children": {
"RLTrainer._checkpoint": {
"total": 1.678179928000418,
"count": 10,
"self": 1.678179928000418
}
}
},
"_update_policy": {
"total": 377.45566532700013,
"count": 97,
"self": 306.30452277000427,
"children": {
"TorchPPOOptimizer.update": {
"total": 71.15114255699586,
"count": 2910,
"self": 71.15114255699586
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0769999789772555e-06,
"count": 1,
"self": 1.0769999789772555e-06
},
"TrainerController._save_models": {
"total": 0.12668901199958782,
"count": 1,
"self": 0.0025510939995001536,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12413791800008767,
"count": 1,
"self": 0.12413791800008767
}
}
}
}
}
}
}