ppo-Huggy / run_logs /timers.json
Curiolearner's picture
Huggy
0bb115c
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4003392457962036,
"min": 1.4003392457962036,
"max": 1.4297887086868286,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70044.96875,
"min": 68850.3515625,
"max": 76919.5,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 84.06122448979592,
"min": 77.1328125,
"max": 421.25210084033614,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49428.0,
"min": 48912.0,
"max": 50232.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999919.0,
"min": 49755.0,
"max": 1999919.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999919.0,
"min": 49755.0,
"max": 1999919.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.470252513885498,
"min": 0.11743412911891937,
"max": 2.4968833923339844,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1452.508544921875,
"min": 13.857227325439453,
"max": 1534.37451171875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.889867730590762,
"min": 1.9039082840337591,
"max": 4.02767930659619,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2287.242225587368,
"min": 224.66117751598358,
"max": 2382.375328063965,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.889867730590762,
"min": 1.9039082840337591,
"max": 4.02767930659619,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2287.242225587368,
"min": 224.66117751598358,
"max": 2382.375328063965,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01515476803219321,
"min": 0.012254402458165715,
"max": 0.019127437319063273,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04546430409657963,
"min": 0.02450880491633143,
"max": 0.05520437834008286,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05656189363863733,
"min": 0.022320866181204716,
"max": 0.07050649368514617,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.169685680915912,
"min": 0.04464173236240943,
"max": 0.2040841771910588,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5648488117500043e-06,
"min": 3.5648488117500043e-06,
"max": 0.00029534265155245005,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0694546435250013e-05,
"min": 1.0694546435250013e-05,
"max": 0.0008441598186133998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10118825,
"min": 0.10118825,
"max": 0.19844755000000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30356475,
"min": 0.20751509999999995,
"max": 0.5813866000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.929367500000008e-05,
"min": 6.929367500000008e-05,
"max": 0.0049225327449999995,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020788102500000024,
"min": 0.00020788102500000024,
"max": 0.014071191339999997,
"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": "1687246958",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1687249337"
},
"total": 2379.019732223,
"count": 1,
"self": 0.4463085030001821,
"children": {
"run_training.setup": {
"total": 0.04231952400004957,
"count": 1,
"self": 0.04231952400004957
},
"TrainerController.start_learning": {
"total": 2378.531104196,
"count": 1,
"self": 4.21135652884368,
"children": {
"TrainerController._reset_env": {
"total": 4.113480365999976,
"count": 1,
"self": 4.113480365999976
},
"TrainerController.advance": {
"total": 2370.088182886156,
"count": 232562,
"self": 4.403281983155011,
"children": {
"env_step": {
"total": 1844.1177394060194,
"count": 232562,
"self": 1556.049686530981,
"children": {
"SubprocessEnvManager._take_step": {
"total": 285.32056528897033,
"count": 232562,
"self": 16.658258556917076,
"children": {
"TorchPolicy.evaluate": {
"total": 268.66230673205325,
"count": 222921,
"self": 268.66230673205325
}
}
},
"workers": {
"total": 2.7474875860681323,
"count": 232562,
"self": 0.0,
"children": {
"worker_root": {
"total": 2370.897938412987,
"count": 232562,
"is_parallel": true,
"self": 1098.9416730460339,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008742579999534428,
"count": 1,
"is_parallel": true,
"self": 0.00024594699993940594,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006283110000140368,
"count": 2,
"is_parallel": true,
"self": 0.0006283110000140368
}
}
},
"UnityEnvironment.step": {
"total": 0.027490637000028073,
"count": 1,
"is_parallel": true,
"self": 0.00030728299998372677,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022946700005377352,
"count": 1,
"is_parallel": true,
"self": 0.00022946700005377352
},
"communicator.exchange": {
"total": 0.02625451599999451,
"count": 1,
"is_parallel": true,
"self": 0.02625451599999451
},
"steps_from_proto": {
"total": 0.0006993709999960629,
"count": 1,
"is_parallel": true,
"self": 0.0001919189999171067,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005074520000789562,
"count": 2,
"is_parallel": true,
"self": 0.0005074520000789562
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1271.9562653669532,
"count": 232561,
"is_parallel": true,
"self": 39.19850754497088,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 78.2626780460397,
"count": 232561,
"is_parallel": true,
"self": 78.2626780460397
},
"communicator.exchange": {
"total": 1059.6811107919889,
"count": 232561,
"is_parallel": true,
"self": 1059.6811107919889
},
"steps_from_proto": {
"total": 94.81396898395383,
"count": 232561,
"is_parallel": true,
"self": 33.670181595945564,
"children": {
"_process_rank_one_or_two_observation": {
"total": 61.14378738800826,
"count": 465122,
"is_parallel": true,
"self": 61.14378738800826
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 521.5671614969816,
"count": 232562,
"self": 6.63372293788359,
"children": {
"process_trajectory": {
"total": 135.42078652009695,
"count": 232562,
"self": 134.1439204730966,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2768660470003397,
"count": 10,
"self": 1.2768660470003397
}
}
},
"_update_policy": {
"total": 379.51265203900107,
"count": 97,
"self": 319.74348790599606,
"children": {
"TorchPPOOptimizer.update": {
"total": 59.769164133005006,
"count": 2910,
"self": 59.769164133005006
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.629999683762435e-07,
"count": 1,
"self": 8.629999683762435e-07
},
"TrainerController._save_models": {
"total": 0.11808355199991638,
"count": 1,
"self": 0.002051061999736703,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11603249000017968,
"count": 1,
"self": 0.11603249000017968
}
}
}
}
}
}
}