ppo-Huggy / run_logs /timers.json
kasunw's picture
Huggy
026f9eb
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4132155179977417,
"min": 1.4132155179977417,
"max": 1.4319323301315308,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69244.734375,
"min": 67050.59375,
"max": 75445.59375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 150.56363636363636,
"min": 108.23851203501094,
"max": 411.655737704918,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49686.0,
"min": 49010.0,
"max": 50288.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999989.0,
"min": 49816.0,
"max": 1999989.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999989.0,
"min": 49816.0,
"max": 1999989.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.212770462036133,
"min": 0.0802818015217781,
"max": 2.3346853256225586,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 730.2142333984375,
"min": 9.71409797668457,
"max": 1064.2384033203125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.2933532234394187,
"min": 1.8293625618800644,
"max": 3.7646455658806697,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1086.8065637350082,
"min": 221.3528699874878,
"max": 1694.0905046463013,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.2933532234394187,
"min": 1.8293625618800644,
"max": 3.7646455658806697,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1086.8065637350082,
"min": 221.3528699874878,
"max": 1694.0905046463013,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017179177737367962,
"min": 0.014430450702460953,
"max": 0.019865545673140635,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.034358355474735924,
"min": 0.02893821608595317,
"max": 0.054417239485580166,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04278997232516607,
"min": 0.02101778999591867,
"max": 0.07645177981919714,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.08557994465033214,
"min": 0.04203557999183734,
"max": 0.2293553394575914,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.2074485975500155e-06,
"min": 4.2074485975500155e-06,
"max": 0.00029536545154485,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.414897195100031e-06,
"min": 8.414897195100031e-06,
"max": 0.0008441172186276001,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10140245000000003,
"min": 0.10140245000000003,
"max": 0.19845515000000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20280490000000007,
"min": 0.20280490000000007,
"max": 0.5813723999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.998225500000028e-05,
"min": 7.998225500000028e-05,
"max": 0.0049229119849999985,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00015996451000000055,
"min": 0.00015996451000000055,
"max": 0.014070482760000003,
"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": "1683625662",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]",
"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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1683629532"
},
"total": 3870.2561034909995,
"count": 1,
"self": 0.496563043999231,
"children": {
"run_training.setup": {
"total": 0.05221413699996447,
"count": 1,
"self": 0.05221413699996447
},
"TrainerController.start_learning": {
"total": 3869.7073263100006,
"count": 1,
"self": 6.282297925896728,
"children": {
"TrainerController._reset_env": {
"total": 1.2132270369999105,
"count": 1,
"self": 1.2132270369999105
},
"TrainerController.advance": {
"total": 3862.079803617104,
"count": 230161,
"self": 5.954300659209821,
"children": {
"env_step": {
"total": 2292.0972479839247,
"count": 230161,
"self": 1951.3762429889914,
"children": {
"SubprocessEnvManager._take_step": {
"total": 336.8244870809565,
"count": 230161,
"self": 21.77904187791387,
"children": {
"TorchPolicy.evaluate": {
"total": 315.0454452030426,
"count": 222929,
"self": 315.0454452030426
}
}
},
"workers": {
"total": 3.8965179139768225,
"count": 230161,
"self": 0.0,
"children": {
"worker_root": {
"total": 3858.983883000999,
"count": 230161,
"is_parallel": true,
"self": 2277.159529731901,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010302690000116854,
"count": 1,
"is_parallel": true,
"self": 0.0002854870000419396,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007447819999697458,
"count": 2,
"is_parallel": true,
"self": 0.0007447819999697458
}
}
},
"UnityEnvironment.step": {
"total": 0.05583445600007053,
"count": 1,
"is_parallel": true,
"self": 0.0004341430000067703,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023482799997509574,
"count": 1,
"is_parallel": true,
"self": 0.00023482799997509574
},
"communicator.exchange": {
"total": 0.05431037200003175,
"count": 1,
"is_parallel": true,
"self": 0.05431037200003175
},
"steps_from_proto": {
"total": 0.0008551130000569174,
"count": 1,
"is_parallel": true,
"self": 0.00024176900012662372,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006133439999302936,
"count": 2,
"is_parallel": true,
"self": 0.0006133439999302936
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1581.8243532690983,
"count": 230160,
"is_parallel": true,
"self": 48.104958620160915,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 78.22986859797004,
"count": 230160,
"is_parallel": true,
"self": 78.22986859797004
},
"communicator.exchange": {
"total": 1337.842708130967,
"count": 230160,
"is_parallel": true,
"self": 1337.842708130967
},
"steps_from_proto": {
"total": 117.64681792000044,
"count": 230160,
"is_parallel": true,
"self": 41.259543379083766,
"children": {
"_process_rank_one_or_two_observation": {
"total": 76.38727454091668,
"count": 460320,
"is_parallel": true,
"self": 76.38727454091668
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1564.0282549739693,
"count": 230161,
"self": 9.617653175924943,
"children": {
"process_trajectory": {
"total": 194.7337051340436,
"count": 230161,
"self": 193.29893267104433,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4347724629992626,
"count": 10,
"self": 1.4347724629992626
}
}
},
"_update_policy": {
"total": 1359.6768966640007,
"count": 96,
"self": 380.84821664198944,
"children": {
"TorchPPOOptimizer.update": {
"total": 978.8286800220112,
"count": 2880,
"self": 978.8286800220112
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.471999874222092e-06,
"count": 1,
"self": 9.471999874222092e-06
},
"TrainerController._save_models": {
"total": 0.13198825800009217,
"count": 1,
"self": 0.0027228460003243526,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12926541199976782,
"count": 1,
"self": 0.12926541199976782
}
}
}
}
}
}
}