ppo-Huggy / run_logs /timers.json
pokjay's picture
Huggy
c111dc4
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4096696376800537,
"min": 1.4096696376800537,
"max": 1.42800772190094,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70606.125,
"min": 67867.84375,
"max": 78755.234375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 78.7846889952153,
"min": 77.103125,
"max": 385.0,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49398.0,
"min": 49025.0,
"max": 50435.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999992.0,
"min": 49816.0,
"max": 1999992.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999992.0,
"min": 49816.0,
"max": 1999992.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.529076337814331,
"min": 0.21762387454509735,
"max": 2.556656837463379,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1585.7308349609375,
"min": 28.29110336303711,
"max": 1596.39111328125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8148037176193044,
"min": 1.7789956425244993,
"max": 4.003713447131858,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2391.8819309473038,
"min": 231.2694335281849,
"max": 2480.177240908146,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8148037176193044,
"min": 1.7789956425244993,
"max": 4.003713447131858,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2391.8819309473038,
"min": 231.2694335281849,
"max": 2480.177240908146,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01697407437443164,
"min": 0.011213880198677847,
"max": 0.021949380812778446,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05092222312329492,
"min": 0.022427760397355695,
"max": 0.059433649935332754,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05737521776722537,
"min": 0.020688506371031205,
"max": 0.06101805046200752,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17212565330167612,
"min": 0.04137701274206241,
"max": 0.18053166282673677,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.4774988408666627e-06,
"min": 3.4774988408666627e-06,
"max": 0.00029528692657102495,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0432496522599989e-05,
"min": 1.0432496522599989e-05,
"max": 0.00084393376868875,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10115913333333333,
"min": 0.10115913333333333,
"max": 0.19842897500000006,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3034774,
"min": 0.20744799999999997,
"max": 0.58131125,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.784075333333328e-05,
"min": 6.784075333333328e-05,
"max": 0.0049216058525,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020352225999999986,
"min": 0.00020352225999999986,
"max": 0.014067431375,
"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": "1701027962",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "1701032362"
},
"total": 4400.911062748,
"count": 1,
"self": 0.5450462660010089,
"children": {
"run_training.setup": {
"total": 0.1078039850000323,
"count": 1,
"self": 0.1078039850000323
},
"TrainerController.start_learning": {
"total": 4400.2582124969995,
"count": 1,
"self": 8.105372971930592,
"children": {
"TrainerController._reset_env": {
"total": 3.0664309470000717,
"count": 1,
"self": 3.0664309470000717
},
"TrainerController.advance": {
"total": 4388.987922071069,
"count": 233031,
"self": 8.441472040046392,
"children": {
"env_step": {
"total": 2815.9096385171274,
"count": 233031,
"self": 2345.32350450993,
"children": {
"SubprocessEnvManager._take_step": {
"total": 465.3745935382045,
"count": 233031,
"self": 28.229054496289905,
"children": {
"TorchPolicy.evaluate": {
"total": 437.1455390419146,
"count": 223004,
"self": 437.1455390419146
}
}
},
"workers": {
"total": 5.21154046899278,
"count": 233031,
"self": 0.0,
"children": {
"worker_root": {
"total": 4387.205957280968,
"count": 233031,
"is_parallel": true,
"self": 2527.936254201838,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010007930000028864,
"count": 1,
"is_parallel": true,
"self": 0.00023911499999940133,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007616780000034851,
"count": 2,
"is_parallel": true,
"self": 0.0007616780000034851
}
}
},
"UnityEnvironment.step": {
"total": 0.038854936999996426,
"count": 1,
"is_parallel": true,
"self": 0.000469479000003048,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001774219999788329,
"count": 1,
"is_parallel": true,
"self": 0.0001774219999788329
},
"communicator.exchange": {
"total": 0.037308762000066054,
"count": 1,
"is_parallel": true,
"self": 0.037308762000066054
},
"steps_from_proto": {
"total": 0.0008992739999484911,
"count": 1,
"is_parallel": true,
"self": 0.00025794899988795805,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006413250000605331,
"count": 2,
"is_parallel": true,
"self": 0.0006413250000605331
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1859.2697030791296,
"count": 233030,
"is_parallel": true,
"self": 58.119285820270306,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 92.49907985202822,
"count": 233030,
"is_parallel": true,
"self": 92.49907985202822
},
"communicator.exchange": {
"total": 1578.2531633628407,
"count": 233030,
"is_parallel": true,
"self": 1578.2531633628407
},
"steps_from_proto": {
"total": 130.39817404399025,
"count": 233030,
"is_parallel": true,
"self": 42.1874557379474,
"children": {
"_process_rank_one_or_two_observation": {
"total": 88.21071830604285,
"count": 466060,
"is_parallel": true,
"self": 88.21071830604285
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1564.6368115138955,
"count": 233031,
"self": 12.423381275845486,
"children": {
"process_trajectory": {
"total": 258.5792350920499,
"count": 233031,
"self": 257.29805591104855,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2811791810013347,
"count": 10,
"self": 1.2811791810013347
}
}
},
"_update_policy": {
"total": 1293.6341951460001,
"count": 97,
"self": 354.61889228202733,
"children": {
"TorchPPOOptimizer.update": {
"total": 939.0153028639728,
"count": 2910,
"self": 939.0153028639728
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1309994079056196e-06,
"count": 1,
"self": 1.1309994079056196e-06
},
"TrainerController._save_models": {
"total": 0.09848537600009877,
"count": 1,
"self": 0.0026306509998903493,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09585472500020842,
"count": 1,
"self": 0.09585472500020842
}
}
}
}
}
}
}