ppo-Huggy / run_logs /timers.json
nlamot's picture
Huggy
10b4d8c
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4068371057510376,
"min": 1.4068371057510376,
"max": 1.4274461269378662,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 72874.1640625,
"min": 68164.453125,
"max": 76607.46875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 84.43931623931624,
"min": 84.43931623931624,
"max": 372.44776119402985,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49397.0,
"min": 48924.0,
"max": 50289.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999913.0,
"min": 49614.0,
"max": 1999913.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999913.0,
"min": 49614.0,
"max": 1999913.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.429692029953003,
"min": -0.04853063449263573,
"max": 2.479243755340576,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1421.369873046875,
"min": -6.4545745849609375,
"max": 1421.369873046875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7832505102850433,
"min": 1.8578070384219176,
"max": 3.900578400100696,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2213.2015485167503,
"min": 247.08833611011505,
"max": 2213.2015485167503,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7832505102850433,
"min": 1.8578070384219176,
"max": 3.900578400100696,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2213.2015485167503,
"min": 247.08833611011505,
"max": 2213.2015485167503,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015579127601631626,
"min": 0.013416597184186686,
"max": 0.019458300663003077,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04673738280489488,
"min": 0.02683319436837337,
"max": 0.05837490198900923,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05789052082432641,
"min": 0.023901062241444983,
"max": 0.06174209151003096,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1736715624729792,
"min": 0.047802124482889966,
"max": 0.18522627453009288,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.2676989108000037e-06,
"min": 3.2676989108000037e-06,
"max": 0.00029532990155669995,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.803096732400011e-06,
"min": 9.803096732400011e-06,
"max": 0.0008437834687388499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10108919999999999,
"min": 0.10108919999999999,
"max": 0.19844330000000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30326759999999997,
"min": 0.20734185000000002,
"max": 0.5812611500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.435108000000008e-05,
"min": 6.435108000000008e-05,
"max": 0.004922320670000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019305324000000023,
"min": 0.00019305324000000023,
"max": 0.014064931385,
"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": "1698842426",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=Huggy --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1698844895"
},
"total": 2469.2895879280004,
"count": 1,
"self": 0.42478378000032535,
"children": {
"run_training.setup": {
"total": 0.04622657799995977,
"count": 1,
"self": 0.04622657799995977
},
"TrainerController.start_learning": {
"total": 2468.81857757,
"count": 1,
"self": 4.541017010961696,
"children": {
"TrainerController._reset_env": {
"total": 8.179689182000061,
"count": 1,
"self": 8.179689182000061
},
"TrainerController.advance": {
"total": 2455.9972894250386,
"count": 232383,
"self": 4.74334889902002,
"children": {
"env_step": {
"total": 1951.3192855220332,
"count": 232383,
"self": 1605.7867859098387,
"children": {
"SubprocessEnvManager._take_step": {
"total": 342.60365169307534,
"count": 232383,
"self": 17.17192180799759,
"children": {
"TorchPolicy.evaluate": {
"total": 325.43172988507774,
"count": 223034,
"self": 325.43172988507774
}
}
},
"workers": {
"total": 2.9288479191191072,
"count": 232383,
"self": 0.0,
"children": {
"worker_root": {
"total": 2460.9512343400797,
"count": 232383,
"is_parallel": true,
"self": 1155.508108557111,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008802790000572713,
"count": 1,
"is_parallel": true,
"self": 0.00027077000004283036,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000609509000014441,
"count": 2,
"is_parallel": true,
"self": 0.000609509000014441
}
}
},
"UnityEnvironment.step": {
"total": 0.028748231000008673,
"count": 1,
"is_parallel": true,
"self": 0.000306743999885839,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002091380000592835,
"count": 1,
"is_parallel": true,
"self": 0.0002091380000592835
},
"communicator.exchange": {
"total": 0.027455292000013287,
"count": 1,
"is_parallel": true,
"self": 0.027455292000013287
},
"steps_from_proto": {
"total": 0.000777057000050263,
"count": 1,
"is_parallel": true,
"self": 0.00023966100013694813,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005373959999133149,
"count": 2,
"is_parallel": true,
"self": 0.0005373959999133149
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1305.4431257829688,
"count": 232382,
"is_parallel": true,
"self": 40.604229627987024,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 88.67188008804271,
"count": 232382,
"is_parallel": true,
"self": 88.67188008804271
},
"communicator.exchange": {
"total": 1083.1424980488855,
"count": 232382,
"is_parallel": true,
"self": 1083.1424980488855
},
"steps_from_proto": {
"total": 93.02451801805375,
"count": 232382,
"is_parallel": true,
"self": 34.9490455880358,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.07547243001795,
"count": 464764,
"is_parallel": true,
"self": 58.07547243001795
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 499.9346550039854,
"count": 232383,
"self": 6.796660313891266,
"children": {
"process_trajectory": {
"total": 155.71842751609267,
"count": 232383,
"self": 154.6079068950927,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1105206209999778,
"count": 10,
"self": 1.1105206209999778
}
}
},
"_update_policy": {
"total": 337.4195671740015,
"count": 97,
"self": 275.59550735299695,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.82405982100454,
"count": 2910,
"self": 61.82405982100454
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.899996828404255e-07,
"count": 1,
"self": 8.899996828404255e-07
},
"TrainerController._save_models": {
"total": 0.10058106199994654,
"count": 1,
"self": 0.002109234999807086,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09847182700013946,
"count": 1,
"self": 0.09847182700013946
}
}
}
}
}
}
}