ppo-Huggy / run_logs /timers.json
loiccabannes's picture
Huggy
a9e72ee verified
raw
history blame
17.4 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.407568335533142,
"min": 1.407568335533142,
"max": 1.429118275642395,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69284.734375,
"min": 67668.5390625,
"max": 76889.5390625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 93.5158878504673,
"min": 76.8177570093458,
"max": 369.42962962962963,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 50031.0,
"min": 48977.0,
"max": 50031.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999827.0,
"min": 49258.0,
"max": 1999827.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999827.0,
"min": 49258.0,
"max": 1999827.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.424834728240967,
"min": 0.11082103848457336,
"max": 2.486980676651001,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1297.28662109375,
"min": 14.850019454956055,
"max": 1574.563720703125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.733285270895913,
"min": 1.8632825114833775,
"max": 4.019294647266689,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1997.3076199293137,
"min": 249.67985653877258,
"max": 2543.369151890278,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.733285270895913,
"min": 1.8632825114833775,
"max": 4.019294647266689,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1997.3076199293137,
"min": 249.67985653877258,
"max": 2543.369151890278,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015869017606342416,
"min": 0.014261316156383447,
"max": 0.02022399170479427,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04760705281902725,
"min": 0.028522632312766895,
"max": 0.056633504810937055,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05329363445440929,
"min": 0.021095030164966982,
"max": 0.060832788422703746,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15988090336322786,
"min": 0.042190060329933964,
"max": 0.17972798608243468,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.773498742199994e-06,
"min": 3.773498742199994e-06,
"max": 0.00029536462654512497,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1320496226599982e-05,
"min": 1.1320496226599982e-05,
"max": 0.0008441235186254999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10125780000000002,
"min": 0.10125780000000002,
"max": 0.19845487499999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3037734000000001,
"min": 0.2076452,
"max": 0.5813745,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.276421999999989e-05,
"min": 7.276421999999989e-05,
"max": 0.004922898262500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021829265999999967,
"min": 0.00021829265999999967,
"max": 0.014070587550000003,
"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": "1710248176",
"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": "1710250756"
},
"total": 2579.4423243210003,
"count": 1,
"self": 0.6414213860007294,
"children": {
"run_training.setup": {
"total": 0.05353991799995583,
"count": 1,
"self": 0.05353991799995583
},
"TrainerController.start_learning": {
"total": 2578.7473630169998,
"count": 1,
"self": 4.614748941906782,
"children": {
"TrainerController._reset_env": {
"total": 2.7827493879999565,
"count": 1,
"self": 2.7827493879999565
},
"TrainerController.advance": {
"total": 2571.224635479093,
"count": 232900,
"self": 5.186559116109038,
"children": {
"env_step": {
"total": 2065.4795833680123,
"count": 232900,
"self": 1712.0657848911542,
"children": {
"SubprocessEnvManager._take_step": {
"total": 350.2990963108805,
"count": 232900,
"self": 17.247371176821048,
"children": {
"TorchPolicy.evaluate": {
"total": 333.05172513405944,
"count": 222946,
"self": 333.05172513405944
}
}
},
"workers": {
"total": 3.1147021659777465,
"count": 232900,
"self": 0.0,
"children": {
"worker_root": {
"total": 2571.1921408717812,
"count": 232900,
"is_parallel": true,
"self": 1191.3651758548785,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001028499999961241,
"count": 1,
"is_parallel": true,
"self": 0.000259189999951559,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000769310000009682,
"count": 2,
"is_parallel": true,
"self": 0.000769310000009682
}
}
},
"UnityEnvironment.step": {
"total": 0.03192386299997452,
"count": 1,
"is_parallel": true,
"self": 0.00040228900002148293,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021426199998586526,
"count": 1,
"is_parallel": true,
"self": 0.00021426199998586526
},
"communicator.exchange": {
"total": 0.030521743000008428,
"count": 1,
"is_parallel": true,
"self": 0.030521743000008428
},
"steps_from_proto": {
"total": 0.0007855689999587412,
"count": 1,
"is_parallel": true,
"self": 0.00022027999989404634,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005652890000646948,
"count": 2,
"is_parallel": true,
"self": 0.0005652890000646948
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1379.8269650169027,
"count": 232899,
"is_parallel": true,
"self": 41.2660768198848,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 90.12815568798192,
"count": 232899,
"is_parallel": true,
"self": 90.12815568798192
},
"communicator.exchange": {
"total": 1151.3796350870414,
"count": 232899,
"is_parallel": true,
"self": 1151.3796350870414
},
"steps_from_proto": {
"total": 97.05309742199472,
"count": 232899,
"is_parallel": true,
"self": 36.84953784986112,
"children": {
"_process_rank_one_or_two_observation": {
"total": 60.2035595721336,
"count": 465798,
"is_parallel": true,
"self": 60.2035595721336
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 500.55849299497174,
"count": 232900,
"self": 7.207000956913134,
"children": {
"process_trajectory": {
"total": 170.79611207405765,
"count": 232900,
"self": 169.57643835005808,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2196737239995628,
"count": 10,
"self": 1.2196737239995628
}
}
},
"_update_policy": {
"total": 322.55537996400096,
"count": 97,
"self": 260.2665852119852,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.28879475201575,
"count": 2910,
"self": 62.28879475201575
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.669999260746408e-07,
"count": 1,
"self": 8.669999260746408e-07
},
"TrainerController._save_models": {
"total": 0.12522834099991087,
"count": 1,
"self": 0.0020957149999958347,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12313262599991504,
"count": 1,
"self": 0.12313262599991504
}
}
}
}
}
}
}