ppo-Huggy / run_logs /timers.json
HanliChu's picture
Huggy
cadf788 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.406597375869751,
"min": 1.406597375869751,
"max": 1.4288474321365356,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68807.9296875,
"min": 68807.9296875,
"max": 77729.28125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 89.959927140255,
"min": 84.51282051282051,
"max": 421.9579831932773,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49388.0,
"min": 48798.0,
"max": 50213.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999928.0,
"min": 49872.0,
"max": 1999928.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999928.0,
"min": 49872.0,
"max": 1999928.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.416571617126465,
"min": 0.022153634577989578,
"max": 2.4822020530700684,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1326.6978759765625,
"min": 2.614128828048706,
"max": 1405.7984619140625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7514728696402737,
"min": 1.7324045463386228,
"max": 3.931966282595369,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2059.5586054325104,
"min": 204.4237364679575,
"max": 2184.1263518333435,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7514728696402737,
"min": 1.7324045463386228,
"max": 3.931966282595369,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2059.5586054325104,
"min": 204.4237364679575,
"max": 2184.1263518333435,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01546471876952435,
"min": 0.01403064677239551,
"max": 0.020474934166607756,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04639415630857305,
"min": 0.029411292502481954,
"max": 0.06142480249982327,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.050506118891967676,
"min": 0.02321233802164594,
"max": 0.06404134780168533,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15151835667590302,
"min": 0.04642467604329188,
"max": 0.17361684925854207,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.448848850416655e-06,
"min": 3.448848850416655e-06,
"max": 0.00029537572654142496,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0346546551249964e-05,
"min": 1.0346546551249964e-05,
"max": 0.0008444697185101,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1011495833333333,
"min": 0.1011495833333333,
"max": 0.198458575,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30344874999999993,
"min": 0.20742799999999995,
"max": 0.5814898999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.736420833333316e-05,
"min": 6.736420833333316e-05,
"max": 0.0049230828925,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020209262499999947,
"min": 0.00020209262499999947,
"max": 0.014076346010000003,
"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": "1710165577",
"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=Huggy3 --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": "1710167963"
},
"total": 2385.580220461,
"count": 1,
"self": 0.4889043629996195,
"children": {
"run_training.setup": {
"total": 0.04995213900019735,
"count": 1,
"self": 0.04995213900019735
},
"TrainerController.start_learning": {
"total": 2385.041363959,
"count": 1,
"self": 4.279403300879949,
"children": {
"TrainerController._reset_env": {
"total": 2.7156588060001923,
"count": 1,
"self": 2.7156588060001923
},
"TrainerController.advance": {
"total": 2377.928589983119,
"count": 232043,
"self": 4.688238739111966,
"children": {
"env_step": {
"total": 1868.7671116400256,
"count": 232043,
"self": 1547.0027026219323,
"children": {
"SubprocessEnvManager._take_step": {
"total": 318.978375818991,
"count": 232043,
"self": 16.807027841293802,
"children": {
"TorchPolicy.evaluate": {
"total": 302.1713479776972,
"count": 222866,
"self": 302.1713479776972
}
}
},
"workers": {
"total": 2.7860331991023486,
"count": 232043,
"self": 0.0,
"children": {
"worker_root": {
"total": 2377.9643711980407,
"count": 232043,
"is_parallel": true,
"self": 1125.229882429067,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008779169997978897,
"count": 1,
"is_parallel": true,
"self": 0.00020129399990764796,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006766229998902418,
"count": 2,
"is_parallel": true,
"self": 0.0006766229998902418
}
}
},
"UnityEnvironment.step": {
"total": 0.029714437000166072,
"count": 1,
"is_parallel": true,
"self": 0.0003704780001498875,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002234920002592844,
"count": 1,
"is_parallel": true,
"self": 0.0002234920002592844
},
"communicator.exchange": {
"total": 0.028347052999833977,
"count": 1,
"is_parallel": true,
"self": 0.028347052999833977
},
"steps_from_proto": {
"total": 0.0007734139999229228,
"count": 1,
"is_parallel": true,
"self": 0.00019148000001223409,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005819339999106887,
"count": 2,
"is_parallel": true,
"self": 0.0005819339999106887
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1252.7344887689737,
"count": 232042,
"is_parallel": true,
"self": 39.088784885083896,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 81.37491871386601,
"count": 232042,
"is_parallel": true,
"self": 81.37491871386601
},
"communicator.exchange": {
"total": 1042.3678837971793,
"count": 232042,
"is_parallel": true,
"self": 1042.3678837971793
},
"steps_from_proto": {
"total": 89.90290137284455,
"count": 232042,
"is_parallel": true,
"self": 31.863620995602105,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.03928037724245,
"count": 464084,
"is_parallel": true,
"self": 58.03928037724245
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 504.47323960398126,
"count": 232043,
"self": 6.567798207060605,
"children": {
"process_trajectory": {
"total": 148.86411335991488,
"count": 232043,
"self": 147.68700643591637,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1771069239985081,
"count": 10,
"self": 1.1771069239985081
}
}
},
"_update_policy": {
"total": 349.04132803700577,
"count": 97,
"self": 283.7967625199981,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.24456551700769,
"count": 2910,
"self": 65.24456551700769
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0040002962341532e-06,
"count": 1,
"self": 1.0040002962341532e-06
},
"TrainerController._save_models": {
"total": 0.11771086500084493,
"count": 1,
"self": 0.002242751001176657,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11546811399966828,
"count": 1,
"self": 0.11546811399966828
}
}
}
}
}
}
}