ppo-Huggy / run_logs /timers.json
Zaleks's picture
Huggy
3ae8e48
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.412270188331604,
"min": 1.4122568368911743,
"max": 1.4316145181655884,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70147.4609375,
"min": 69093.9375,
"max": 77856.8203125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 117.28333333333333,
"min": 98.726,
"max": 387.3720930232558,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49259.0,
"min": 49000.0,
"max": 50031.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999924.0,
"min": 49954.0,
"max": 1999924.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999924.0,
"min": 49954.0,
"max": 1999924.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.2481119632720947,
"min": 0.17313149571418762,
"max": 2.346055030822754,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 944.20703125,
"min": 22.160831451416016,
"max": 1170.16259765625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.5011975390570504,
"min": 1.8083898494951427,
"max": 3.8492115495052746,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1470.5029664039612,
"min": 231.47390073537827,
"max": 1840.9676812291145,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.5011975390570504,
"min": 1.8083898494951427,
"max": 3.8492115495052746,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1470.5029664039612,
"min": 231.47390073537827,
"max": 1840.9676812291145,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015144094790593955,
"min": 0.013629339750817357,
"max": 0.019389774183703898,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03028818958118791,
"min": 0.03028818958118791,
"max": 0.05750349373459661,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.044131475997467834,
"min": 0.021238758073498804,
"max": 0.06339141707867384,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.08826295199493567,
"min": 0.04247751614699761,
"max": 0.1833916333814462,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.668248443949994e-06,
"min": 4.668248443949994e-06,
"max": 0.00029535900154699997,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.336496887899988e-06,
"min": 9.336496887899988e-06,
"max": 0.0008441227686257498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10155605000000004,
"min": 0.10155605000000004,
"max": 0.19845300000000007,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20311210000000007,
"min": 0.20311210000000007,
"max": 0.58137425,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.764689499999987e-05,
"min": 8.764689499999987e-05,
"max": 0.0049228047,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00017529378999999975,
"min": 0.00017529378999999975,
"max": 0.014070575074999996,
"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": "1680013475",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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": "1680015803"
},
"total": 2328.244451659,
"count": 1,
"self": 0.42011361699996996,
"children": {
"run_training.setup": {
"total": 0.19100252100008674,
"count": 1,
"self": 0.19100252100008674
},
"TrainerController.start_learning": {
"total": 2327.633335521,
"count": 1,
"self": 4.174175373083926,
"children": {
"TrainerController._reset_env": {
"total": 9.285937805000003,
"count": 1,
"self": 9.285937805000003
},
"TrainerController.advance": {
"total": 2314.048221132916,
"count": 230513,
"self": 4.531055896930411,
"children": {
"env_step": {
"total": 1806.3894942629797,
"count": 230513,
"self": 1523.7424738108962,
"children": {
"SubprocessEnvManager._take_step": {
"total": 279.92897229904656,
"count": 230513,
"self": 17.006209858220927,
"children": {
"TorchPolicy.evaluate": {
"total": 262.92276244082564,
"count": 222902,
"self": 262.92276244082564
}
}
},
"workers": {
"total": 2.718048153036989,
"count": 230513,
"self": 0.0,
"children": {
"worker_root": {
"total": 2319.7444312330695,
"count": 230513,
"is_parallel": true,
"self": 1078.6875761040596,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011847399999851405,
"count": 1,
"is_parallel": true,
"self": 0.0003220900000542315,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000862649999930909,
"count": 2,
"is_parallel": true,
"self": 0.000862649999930909
}
}
},
"UnityEnvironment.step": {
"total": 0.029025937000028534,
"count": 1,
"is_parallel": true,
"self": 0.00036827900009939185,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021223499993539008,
"count": 1,
"is_parallel": true,
"self": 0.00021223499993539008
},
"communicator.exchange": {
"total": 0.027612152999950013,
"count": 1,
"is_parallel": true,
"self": 0.027612152999950013
},
"steps_from_proto": {
"total": 0.0008332700000437399,
"count": 1,
"is_parallel": true,
"self": 0.00024191700003939332,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005913530000043465,
"count": 2,
"is_parallel": true,
"self": 0.0005913530000043465
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1241.0568551290098,
"count": 230512,
"is_parallel": true,
"self": 37.914889397986144,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 77.78013929798567,
"count": 230512,
"is_parallel": true,
"self": 77.78013929798567
},
"communicator.exchange": {
"total": 1037.6191893340151,
"count": 230512,
"is_parallel": true,
"self": 1037.6191893340151
},
"steps_from_proto": {
"total": 87.74263709902289,
"count": 230512,
"is_parallel": true,
"self": 32.80198230203803,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.94065479698486,
"count": 461024,
"is_parallel": true,
"self": 54.94065479698486
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 503.1276709730056,
"count": 230513,
"self": 6.717944667896063,
"children": {
"process_trajectory": {
"total": 135.70351082910884,
"count": 230513,
"self": 134.35013383610828,
"children": {
"RLTrainer._checkpoint": {
"total": 1.353376993000552,
"count": 10,
"self": 1.353376993000552
}
}
},
"_update_policy": {
"total": 360.7062154760007,
"count": 96,
"self": 303.1198490809936,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.586366395007076,
"count": 2880,
"self": 57.586366395007076
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.99999883788405e-07,
"count": 1,
"self": 9.99999883788405e-07
},
"TrainerController._save_models": {
"total": 0.1250002100000529,
"count": 1,
"self": 0.003668370000013965,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12133184000003894,
"count": 1,
"self": 0.12133184000003894
}
}
}
}
}
}
}