ppo-Huggy / run_logs /timers.json
shimooper's picture
Huggy
07d9a40 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4213895797729492,
"min": 1.4189401865005493,
"max": 1.4213895797729492,
"count": 4
},
"Huggy.Policy.Entropy.sum": {
"value": 70505.1875,
"min": 70069.71875,
"max": 77052.7109375,
"count": 4
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 271.4863387978142,
"min": 271.4863387978142,
"max": 391.6875,
"count": 4
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49682.0,
"min": 49601.0,
"max": 50136.0,
"count": 4
},
"Huggy.Step.mean": {
"value": 199814.0,
"min": 49787.0,
"max": 199814.0,
"count": 4
},
"Huggy.Step.sum": {
"value": 199814.0,
"min": 49787.0,
"max": 199814.0,
"count": 4
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.8184615969657898,
"min": 0.034904614090919495,
"max": 0.8184615969657898,
"count": 4
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 149.77847290039062,
"min": 4.432886123657227,
"max": 149.77847290039062,
"count": 4
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.3373911081116057,
"min": 1.8369637901388753,
"max": 3.3373911081116057,
"count": 4
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 610.7425727844238,
"min": 233.29440134763718,
"max": 610.7425727844238,
"count": 4
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.3373911081116057,
"min": 1.8369637901388753,
"max": 3.3373911081116057,
"count": 4
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 610.7425727844238,
"min": 233.29440134763718,
"max": 610.7425727844238,
"count": 4
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015496767992044625,
"min": 0.01433981414399265,
"max": 0.016139594037667848,
"count": 4
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03099353598408925,
"min": 0.0286796282879853,
"max": 0.047909431108079534,
"count": 4
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.029086991275350253,
"min": 0.0222095901456972,
"max": 0.030276791751384736,
"count": 4
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.058173982550700505,
"min": 0.0444191802913944,
"max": 0.07750091714163622,
"count": 4
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.6258087914e-05,
"min": 3.6258087914e-05,
"max": 0.00025278526573825004,
"count": 4
},
"Huggy.Policy.LearningRate.sum": {
"value": 7.2516175828e-05,
"min": 7.2516175828e-05,
"max": 0.0005055705314765001,
"count": 4
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.11208599999999998,
"min": 0.11208599999999998,
"max": 0.18426174999999995,
"count": 4
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.22417199999999995,
"min": 0.22417199999999995,
"max": 0.41378099999999995,
"count": 4
},
"Huggy.Policy.Beta.mean": {
"value": 0.0006130913999999999,
"min": 0.0006130913999999999,
"max": 0.004214661325,
"count": 4
},
"Huggy.Policy.Beta.sum": {
"value": 0.0012261827999999998,
"min": 0.0012261827999999998,
"max": 0.00842932265,
"count": 4
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 4
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 4
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1741872923",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1741873317"
},
"total": 394.54394540400017,
"count": 1,
"self": 0.9029499980006221,
"children": {
"run_training.setup": {
"total": 0.10390590399993016,
"count": 1,
"self": 0.10390590399993016
},
"TrainerController.start_learning": {
"total": 393.5370895019996,
"count": 1,
"self": 0.7472667989604815,
"children": {
"TrainerController._reset_env": {
"total": 4.555670437000117,
"count": 1,
"self": 4.555670437000117
},
"TrainerController.advance": {
"total": 388.0099817490395,
"count": 22870,
"self": 0.7060886300214406,
"children": {
"env_step": {
"total": 256.2906005950085,
"count": 22870,
"self": 212.17636680004262,
"children": {
"SubprocessEnvManager._take_step": {
"total": 43.65573138997661,
"count": 22870,
"self": 2.4700147689418372,
"children": {
"TorchPolicy.evaluate": {
"total": 41.18571662103477,
"count": 22550,
"self": 41.18571662103477
}
}
},
"workers": {
"total": 0.4585024049893036,
"count": 22870,
"self": 0.0,
"children": {
"worker_root": {
"total": 391.8430222460124,
"count": 22870,
"is_parallel": true,
"self": 221.72365879100334,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002763367000170547,
"count": 1,
"is_parallel": true,
"self": 0.000374190999991697,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00238917600017885,
"count": 2,
"is_parallel": true,
"self": 0.00238917600017885
}
}
},
"UnityEnvironment.step": {
"total": 0.04168360299991036,
"count": 1,
"is_parallel": true,
"self": 0.00034664799977690564,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023232400008055265,
"count": 1,
"is_parallel": true,
"self": 0.00023232400008055265
},
"communicator.exchange": {
"total": 0.03985625899986189,
"count": 1,
"is_parallel": true,
"self": 0.03985625899986189
},
"steps_from_proto": {
"total": 0.0012483720001910115,
"count": 1,
"is_parallel": true,
"self": 0.00025062300028366735,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0009977489999073441,
"count": 2,
"is_parallel": true,
"self": 0.0009977489999073441
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 170.11936345500908,
"count": 22869,
"is_parallel": true,
"self": 5.161476417958511,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 10.141836286988564,
"count": 22869,
"is_parallel": true,
"self": 10.141836286988564
},
"communicator.exchange": {
"total": 142.72275534405162,
"count": 22869,
"is_parallel": true,
"self": 142.72275534405162
},
"steps_from_proto": {
"total": 12.093295406010384,
"count": 22869,
"is_parallel": true,
"self": 3.9691780440498405,
"children": {
"_process_rank_one_or_two_observation": {
"total": 8.124117361960543,
"count": 45738,
"is_parallel": true,
"self": 8.124117361960543
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 131.01329252400956,
"count": 22870,
"self": 1.1612087279863772,
"children": {
"process_trajectory": {
"total": 19.211918177023563,
"count": 22870,
"self": 18.83500176102325,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3769164160003129,
"count": 1,
"self": 0.3769164160003129
}
}
},
"_update_policy": {
"total": 110.64016561899962,
"count": 9,
"self": 27.69902469500221,
"children": {
"TorchPPOOptimizer.update": {
"total": 82.94114092399741,
"count": 270,
"self": 82.94114092399741
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.776999852154404e-06,
"count": 1,
"self": 1.776999852154404e-06
},
"TrainerController._save_models": {
"total": 0.22416873999964082,
"count": 1,
"self": 0.004091216999768221,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2200775229998726,
"count": 1,
"self": 0.2200775229998726
}
}
}
}
}
}
}