ppo-Huggy / run_logs /timers.json
MadFritz's picture
Huggy
60cfe05
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.405523657798767,
"min": 1.405523657798767,
"max": 1.4280803203582764,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71094.1953125,
"min": 68605.75,
"max": 77253.1796875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 111.24663677130044,
"min": 91.65862708719851,
"max": 416.03333333333336,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49616.0,
"min": 49000.0,
"max": 50016.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999963.0,
"min": 49607.0,
"max": 1999963.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999963.0,
"min": 49607.0,
"max": 1999963.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.361440896987915,
"min": 0.16833892464637756,
"max": 2.3876781463623047,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1053.20263671875,
"min": 20.032331466674805,
"max": 1268.5709228515625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6792440676368408,
"min": 1.6991091060037373,
"max": 3.885474703295738,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1640.9428541660309,
"min": 202.19398361444473,
"max": 2005.7962446212769,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6792440676368408,
"min": 1.6991091060037373,
"max": 3.885474703295738,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1640.9428541660309,
"min": 202.19398361444473,
"max": 2005.7962446212769,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015066606320680067,
"min": 0.013773461352927067,
"max": 0.020795528390186113,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0451998189620402,
"min": 0.027546922705854134,
"max": 0.06238658517055834,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04542199025551478,
"min": 0.02019037160401543,
"max": 0.05529989492562082,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.13626597076654434,
"min": 0.04038074320803086,
"max": 0.16589968477686245,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.262848912416659e-06,
"min": 3.262848912416659e-06,
"max": 0.000295377976540675,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.788546737249978e-06,
"min": 9.788546737249978e-06,
"max": 0.0008444830685056499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10108758333333334,
"min": 0.10108758333333334,
"max": 0.198459325,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30326275,
"min": 0.20734955,
"max": 0.5814943500000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.427040833333318e-05,
"min": 6.427040833333318e-05,
"max": 0.0049231203175,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019281122499999954,
"min": 0.00019281122499999954,
"max": 0.014076568064999998,
"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": "1701767285",
"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=Huggy --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1701769785"
},
"total": 2499.961307079,
"count": 1,
"self": 0.4392576770001142,
"children": {
"run_training.setup": {
"total": 0.05753043599997909,
"count": 1,
"self": 0.05753043599997909
},
"TrainerController.start_learning": {
"total": 2499.464518966,
"count": 1,
"self": 4.4915691170194805,
"children": {
"TrainerController._reset_env": {
"total": 4.484171155000013,
"count": 1,
"self": 4.484171155000013
},
"TrainerController.advance": {
"total": 2490.383948813981,
"count": 231528,
"self": 4.81418221886679,
"children": {
"env_step": {
"total": 1967.102452954062,
"count": 231528,
"self": 1630.766381748063,
"children": {
"SubprocessEnvManager._take_step": {
"total": 333.41116753707524,
"count": 231528,
"self": 16.98241429119321,
"children": {
"TorchPolicy.evaluate": {
"total": 316.42875324588204,
"count": 222968,
"self": 316.42875324588204
}
}
},
"workers": {
"total": 2.924903668923889,
"count": 231528,
"self": 0.0,
"children": {
"worker_root": {
"total": 2492.1493313179253,
"count": 231528,
"is_parallel": true,
"self": 1166.005873908832,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008655500000713801,
"count": 1,
"is_parallel": true,
"self": 0.0002214500000263797,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006441000000450003,
"count": 2,
"is_parallel": true,
"self": 0.0006441000000450003
}
}
},
"UnityEnvironment.step": {
"total": 0.029283867000003738,
"count": 1,
"is_parallel": true,
"self": 0.00030454699981419253,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020802800008823397,
"count": 1,
"is_parallel": true,
"self": 0.00020802800008823397
},
"communicator.exchange": {
"total": 0.028084218999993027,
"count": 1,
"is_parallel": true,
"self": 0.028084218999993027
},
"steps_from_proto": {
"total": 0.0006870730001082848,
"count": 1,
"is_parallel": true,
"self": 0.0002086140002575121,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00047845899985077267,
"count": 2,
"is_parallel": true,
"self": 0.00047845899985077267
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1326.1434574090933,
"count": 231527,
"is_parallel": true,
"self": 40.963576509911036,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 84.2607920530993,
"count": 231527,
"is_parallel": true,
"self": 84.2607920530993
},
"communicator.exchange": {
"total": 1108.3222079500326,
"count": 231527,
"is_parallel": true,
"self": 1108.3222079500326
},
"steps_from_proto": {
"total": 92.59688089605038,
"count": 231527,
"is_parallel": true,
"self": 32.40351045997272,
"children": {
"_process_rank_one_or_two_observation": {
"total": 60.19337043607766,
"count": 463054,
"is_parallel": true,
"self": 60.19337043607766
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 518.4673136410522,
"count": 231528,
"self": 7.093259460130412,
"children": {
"process_trajectory": {
"total": 155.27871344292157,
"count": 231528,
"self": 154.1222481879213,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1564652550002847,
"count": 10,
"self": 1.1564652550002847
}
}
},
"_update_policy": {
"total": 356.09534073800023,
"count": 97,
"self": 291.65434864300255,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.44099209499768,
"count": 2910,
"self": 64.44099209499768
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.440000212634914e-07,
"count": 1,
"self": 9.440000212634914e-07
},
"TrainerController._save_models": {
"total": 0.10482893599964882,
"count": 1,
"self": 0.00177090799979851,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10305802799985031,
"count": 1,
"self": 0.10305802799985031
}
}
}
}
}
}
}