ppo-Huggy / run_logs /timers.json
twnatelo's picture
Huggy
163efdf verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4063477516174316,
"min": 1.4063477516174316,
"max": 1.4286128282546997,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70337.078125,
"min": 68821.5625,
"max": 77766.953125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 79.14285714285714,
"min": 72.01178203240059,
"max": 401.456,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49306.0,
"min": 48896.0,
"max": 50182.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999960.0,
"min": 49841.0,
"max": 1999960.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999960.0,
"min": 49841.0,
"max": 1999960.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4528372287750244,
"min": 0.02745121717453003,
"max": 2.5408339500427246,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1528.1175537109375,
"min": 3.4039509296417236,
"max": 1670.475830078125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7571423560811468,
"min": 1.6771823817924145,
"max": 4.054063427637494,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2340.6996878385544,
"min": 207.9706153422594,
"max": 2601.4992048740387,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7571423560811468,
"min": 1.6771823817924145,
"max": 4.054063427637494,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2340.6996878385544,
"min": 207.9706153422594,
"max": 2601.4992048740387,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017281992081552743,
"min": 0.013807237627891784,
"max": 0.019515635650734314,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05184597624465823,
"min": 0.027614475255783567,
"max": 0.05854690695220294,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.055257948612173396,
"min": 0.02325254644577702,
"max": 0.05988563117053774,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1657738458365202,
"min": 0.04650509289155404,
"max": 0.1796568935116132,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.856648714483337e-06,
"min": 3.856648714483337e-06,
"max": 0.00029538712653762487,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1569946143450012e-05,
"min": 1.1569946143450012e-05,
"max": 0.0008443318685560498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10128551666666667,
"min": 0.10128551666666667,
"max": 0.19846237500000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30385655,
"min": 0.20769975000000004,
"max": 0.5814439499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.414728166666675e-05,
"min": 7.414728166666675e-05,
"max": 0.004923272512500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022244184500000024,
"min": 0.00022244184500000024,
"max": 0.014074053105000003,
"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": "1735633507",
"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": "1735636238"
},
"total": 2730.794212736,
"count": 1,
"self": 0.4760468059998857,
"children": {
"run_training.setup": {
"total": 0.060259169000005386,
"count": 1,
"self": 0.060259169000005386
},
"TrainerController.start_learning": {
"total": 2730.2579067610004,
"count": 1,
"self": 5.575638349925157,
"children": {
"TrainerController._reset_env": {
"total": 6.090329653000026,
"count": 1,
"self": 6.090329653000026
},
"TrainerController.advance": {
"total": 2718.4727319590756,
"count": 233360,
"self": 5.544965418131596,
"children": {
"env_step": {
"total": 2165.5114863429562,
"count": 233360,
"self": 1704.7920006848872,
"children": {
"SubprocessEnvManager._take_step": {
"total": 457.1854467500746,
"count": 233360,
"self": 18.76237765907075,
"children": {
"TorchPolicy.evaluate": {
"total": 438.42306909100387,
"count": 222940,
"self": 438.42306909100387
}
}
},
"workers": {
"total": 3.534038907994443,
"count": 233360,
"self": 0.0,
"children": {
"worker_root": {
"total": 2721.9697263270245,
"count": 233360,
"is_parallel": true,
"self": 1345.894429319105,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009949269999651733,
"count": 1,
"is_parallel": true,
"self": 0.0003141259999779322,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006808009999872411,
"count": 2,
"is_parallel": true,
"self": 0.0006808009999872411
}
}
},
"UnityEnvironment.step": {
"total": 0.031093798000028983,
"count": 1,
"is_parallel": true,
"self": 0.0004131750000055945,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021946199996136784,
"count": 1,
"is_parallel": true,
"self": 0.00021946199996136784
},
"communicator.exchange": {
"total": 0.029625999000018055,
"count": 1,
"is_parallel": true,
"self": 0.029625999000018055
},
"steps_from_proto": {
"total": 0.0008351620000439652,
"count": 1,
"is_parallel": true,
"self": 0.00023506600001610423,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000600096000027861,
"count": 2,
"is_parallel": true,
"self": 0.000600096000027861
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1376.0752970079195,
"count": 233359,
"is_parallel": true,
"self": 41.525398997976254,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 89.29682559991096,
"count": 233359,
"is_parallel": true,
"self": 89.29682559991096
},
"communicator.exchange": {
"total": 1145.6310338199946,
"count": 233359,
"is_parallel": true,
"self": 1145.6310338199946
},
"steps_from_proto": {
"total": 99.62203859003773,
"count": 233359,
"is_parallel": true,
"self": 37.193921581004304,
"children": {
"_process_rank_one_or_two_observation": {
"total": 62.42811700903343,
"count": 466718,
"is_parallel": true,
"self": 62.42811700903343
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 547.4162801979878,
"count": 233360,
"self": 8.58778359294979,
"children": {
"process_trajectory": {
"total": 190.47852424603997,
"count": 233360,
"self": 188.96964624404012,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5088780019998467,
"count": 10,
"self": 1.5088780019998467
}
}
},
"_update_policy": {
"total": 348.34997235899806,
"count": 97,
"self": 279.56593137600686,
"children": {
"TorchPPOOptimizer.update": {
"total": 68.7840409829912,
"count": 2910,
"self": 68.7840409829912
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.020999661704991e-06,
"count": 1,
"self": 1.020999661704991e-06
},
"TrainerController._save_models": {
"total": 0.11920577799992316,
"count": 1,
"self": 0.0021353659999476804,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11707041199997548,
"count": 1,
"self": 0.11707041199997548
}
}
}
}
}
}
}