ppo-Huggy / run_logs /timers.json
TTony's picture
Huggy
89af772 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4069595336914062,
"min": 1.4069595336914062,
"max": 1.43100106716156,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70400.03125,
"min": 68591.078125,
"max": 78956.203125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 76.76589147286822,
"min": 69.19971870604782,
"max": 397.8253968253968,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49514.0,
"min": 49201.0,
"max": 50126.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999429.0,
"min": 49992.0,
"max": 1999429.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999429.0,
"min": 49992.0,
"max": 1999429.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4785850048065186,
"min": 0.06845264136791229,
"max": 2.515312433242798,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1598.6873779296875,
"min": 8.556580543518066,
"max": 1715.443115234375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.892843376850897,
"min": 1.906990761756897,
"max": 4.049242324936084,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2510.8839780688286,
"min": 238.37384521961212,
"max": 2748.4871085882187,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.892843376850897,
"min": 1.906990761756897,
"max": 4.049242324936084,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2510.8839780688286,
"min": 238.37384521961212,
"max": 2748.4871085882187,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016259332644080537,
"min": 0.013411579164191305,
"max": 0.02060894414704914,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04877799793224161,
"min": 0.02682315832838261,
"max": 0.0587823468738255,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05609344695177343,
"min": 0.021516693104058505,
"max": 0.06122746268908183,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1682803408553203,
"min": 0.04303338620811701,
"max": 0.16836064606904982,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.080048640016676e-06,
"min": 4.080048640016676e-06,
"max": 0.0002952796515734499,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.2240145920050028e-05,
"min": 1.2240145920050028e-05,
"max": 0.0008440020186659998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10135998333333336,
"min": 0.10135998333333336,
"max": 0.19842655000000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3040799500000001,
"min": 0.20786430000000006,
"max": 0.581334,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.786316833333352e-05,
"min": 7.786316833333352e-05,
"max": 0.004921484845000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00023358950500000056,
"min": 0.00023358950500000056,
"max": 0.014068566600000002,
"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": "1767159964",
"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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1767162512"
},
"total": 2547.8315256520004,
"count": 1,
"self": 0.5020373340003061,
"children": {
"run_training.setup": {
"total": 0.02767950399993424,
"count": 1,
"self": 0.02767950399993424
},
"TrainerController.start_learning": {
"total": 2547.301808814,
"count": 1,
"self": 4.28654469784442,
"children": {
"TrainerController._reset_env": {
"total": 3.393043915000135,
"count": 1,
"self": 3.393043915000135
},
"TrainerController.advance": {
"total": 2539.5278058101553,
"count": 233345,
"self": 4.401780678172599,
"children": {
"env_step": {
"total": 2077.9855441439668,
"count": 233345,
"self": 1675.2376136850219,
"children": {
"SubprocessEnvManager._take_step": {
"total": 400.0914513688831,
"count": 233345,
"self": 15.305593846735746,
"children": {
"TorchPolicy.evaluate": {
"total": 384.78585752214735,
"count": 222932,
"self": 384.78585752214735
}
}
},
"workers": {
"total": 2.6564790900617936,
"count": 233345,
"self": 0.0,
"children": {
"worker_root": {
"total": 2534.6464965439823,
"count": 233345,
"is_parallel": true,
"self": 1180.5199110139724,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008728650000193738,
"count": 1,
"is_parallel": true,
"self": 0.00028238599998076097,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005904790000386129,
"count": 2,
"is_parallel": true,
"self": 0.0005904790000386129
}
}
},
"UnityEnvironment.step": {
"total": 0.03054432299995824,
"count": 1,
"is_parallel": true,
"self": 0.0003182790001119429,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023161900003287883,
"count": 1,
"is_parallel": true,
"self": 0.00023161900003287883
},
"communicator.exchange": {
"total": 0.029132531999948696,
"count": 1,
"is_parallel": true,
"self": 0.029132531999948696
},
"steps_from_proto": {
"total": 0.0008618929998647218,
"count": 1,
"is_parallel": true,
"self": 0.00037550000001829176,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00048639299984643003,
"count": 2,
"is_parallel": true,
"self": 0.00048639299984643003
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1354.1265855300098,
"count": 233344,
"is_parallel": true,
"self": 38.63786644804395,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.64991319800038,
"count": 233344,
"is_parallel": true,
"self": 82.64991319800038
},
"communicator.exchange": {
"total": 1141.5482490639006,
"count": 233344,
"is_parallel": true,
"self": 1141.5482490639006
},
"steps_from_proto": {
"total": 91.29055682006492,
"count": 233344,
"is_parallel": true,
"self": 32.9094842129341,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.38107260713082,
"count": 466688,
"is_parallel": true,
"self": 58.38107260713082
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 457.1404809880157,
"count": 233345,
"self": 6.209934365963363,
"children": {
"process_trajectory": {
"total": 156.26825689805105,
"count": 233345,
"self": 155.14190888605094,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1263480120001077,
"count": 10,
"self": 1.1263480120001077
}
}
},
"_update_policy": {
"total": 294.6622897240013,
"count": 97,
"self": 233.18215444001726,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.480135283984055,
"count": 2910,
"self": 61.480135283984055
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.799999366397969e-07,
"count": 1,
"self": 7.799999366397969e-07
},
"TrainerController._save_models": {
"total": 0.09441361100016366,
"count": 1,
"self": 0.0014593250007237657,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09295428599943989,
"count": 1,
"self": 0.09295428599943989
}
}
}
}
}
}
}