ppo-Huggy / run_logs /timers.json
Dante8738's picture
Huggy
8143b55 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.406337022781372,
"min": 1.406337022781372,
"max": 1.4276930093765259,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71046.7421875,
"min": 68901.859375,
"max": 76907.1171875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 69.42897327707455,
"min": 69.42897327707455,
"max": 386.4230769230769,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49364.0,
"min": 48672.0,
"max": 50235.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999982.0,
"min": 49703.0,
"max": 1999982.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999982.0,
"min": 49703.0,
"max": 1999982.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.535346508026123,
"min": 0.11620741337537766,
"max": 2.5460803508758545,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1802.63134765625,
"min": 14.990756034851074,
"max": 1802.63134765625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.9535565492808398,
"min": 2.00166039503822,
"max": 4.041353835357918,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2810.978706538677,
"min": 258.2141909599304,
"max": 2810.978706538677,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.9535565492808398,
"min": 2.00166039503822,
"max": 4.041353835357918,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2810.978706538677,
"min": 258.2141909599304,
"max": 2810.978706538677,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014854512032373654,
"min": 0.013765508142175045,
"max": 0.019969814041784655,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.044563536097120965,
"min": 0.02753101628435009,
"max": 0.05791231677867472,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06177471085555023,
"min": 0.023362783653040727,
"max": 0.06596905644983053,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1853241325666507,
"min": 0.046725567306081454,
"max": 0.1853241325666507,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.942548685849997e-06,
"min": 3.942548685849997e-06,
"max": 0.00029532382655872495,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1827646057549991e-05,
"min": 1.1827646057549991e-05,
"max": 0.0008440401186533001,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10131415000000003,
"min": 0.10131415000000003,
"max": 0.19844127500000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3039424500000001,
"min": 0.20776715,
"max": 0.5813467000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.557608499999997e-05,
"min": 7.557608499999997e-05,
"max": 0.004922219622500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022672825499999992,
"min": 0.00022672825499999992,
"max": 0.014069200330000003,
"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": "1709293550",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/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": "1709295936"
},
"total": 2385.973869871,
"count": 1,
"self": 0.44032738599980803,
"children": {
"run_training.setup": {
"total": 0.05283656799997516,
"count": 1,
"self": 0.05283656799997516
},
"TrainerController.start_learning": {
"total": 2385.480705917,
"count": 1,
"self": 4.449478255995928,
"children": {
"TrainerController._reset_env": {
"total": 3.784090148999894,
"count": 1,
"self": 3.784090148999894
},
"TrainerController.advance": {
"total": 2377.1381877380036,
"count": 233668,
"self": 4.602833062048376,
"children": {
"env_step": {
"total": 1890.6744667400728,
"count": 233668,
"self": 1565.4004636892726,
"children": {
"SubprocessEnvManager._take_step": {
"total": 322.524702256778,
"count": 233668,
"self": 16.841170505915215,
"children": {
"TorchPolicy.evaluate": {
"total": 305.6835317508628,
"count": 222934,
"self": 305.6835317508628
}
}
},
"workers": {
"total": 2.749300794022247,
"count": 233668,
"self": 0.0,
"children": {
"worker_root": {
"total": 2378.0850852240483,
"count": 233668,
"is_parallel": true,
"self": 1097.3770071332087,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009731239999837271,
"count": 1,
"is_parallel": true,
"self": 0.00026172099978793995,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007114030001957872,
"count": 2,
"is_parallel": true,
"self": 0.0007114030001957872
}
}
},
"UnityEnvironment.step": {
"total": 0.030116521000081775,
"count": 1,
"is_parallel": true,
"self": 0.0003138270001272758,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020654800005104335,
"count": 1,
"is_parallel": true,
"self": 0.00020654800005104335
},
"communicator.exchange": {
"total": 0.02888136100000338,
"count": 1,
"is_parallel": true,
"self": 0.02888136100000338
},
"steps_from_proto": {
"total": 0.0007147849999000755,
"count": 1,
"is_parallel": true,
"self": 0.0002020459999130253,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005127389999870502,
"count": 2,
"is_parallel": true,
"self": 0.0005127389999870502
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1280.7080780908395,
"count": 233667,
"is_parallel": true,
"self": 40.785490719928475,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.514474892017,
"count": 233667,
"is_parallel": true,
"self": 82.514474892017
},
"communicator.exchange": {
"total": 1066.5670503329825,
"count": 233667,
"is_parallel": true,
"self": 1066.5670503329825
},
"steps_from_proto": {
"total": 90.84106214591156,
"count": 233667,
"is_parallel": true,
"self": 32.07957632510556,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.761485820806,
"count": 467334,
"is_parallel": true,
"self": 58.761485820806
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 481.8608879358824,
"count": 233668,
"self": 6.299301108893587,
"children": {
"process_trajectory": {
"total": 153.9091038499896,
"count": 233668,
"self": 152.7034569449895,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2056469050000942,
"count": 10,
"self": 1.2056469050000942
}
}
},
"_update_policy": {
"total": 321.6524829769992,
"count": 97,
"self": 257.8388860019991,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.81359697500011,
"count": 2910,
"self": 63.81359697500011
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.890002962085418e-07,
"count": 1,
"self": 7.890002962085418e-07
},
"TrainerController._save_models": {
"total": 0.10894898500009731,
"count": 1,
"self": 0.0019393410002521705,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10700964399984514,
"count": 1,
"self": 0.10700964399984514
}
}
}
}
}
}
}