ppo-Huggy / run_logs /timers.json
quantux's picture
Huggy
1b26eb5
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4083151817321777,
"min": 1.4083151817321777,
"max": 1.4299193620681763,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71153.71875,
"min": 69087.875,
"max": 77000.21875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 85.43835616438356,
"min": 72.59204712812961,
"max": 425.2881355932203,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49896.0,
"min": 48982.0,
"max": 50184.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999791.0,
"min": 49936.0,
"max": 1999791.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999791.0,
"min": 49936.0,
"max": 1999791.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4392197132110596,
"min": 0.04857420176267624,
"max": 2.531717538833618,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1424.5042724609375,
"min": 5.6831817626953125,
"max": 1690.159912109375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7327600823689813,
"min": 1.8778636093832488,
"max": 4.0418824669030995,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2179.931888103485,
"min": 219.71004229784012,
"max": 2639.718222260475,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7327600823689813,
"min": 1.8778636093832488,
"max": 4.0418824669030995,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2179.931888103485,
"min": 219.71004229784012,
"max": 2639.718222260475,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016781482465416452,
"min": 0.013111529856299362,
"max": 0.020386551175033674,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05034444739624935,
"min": 0.026223059712598723,
"max": 0.056878692001919265,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.053654006578856044,
"min": 0.02221601183215777,
"max": 0.06610338358829418,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16096201973656812,
"min": 0.04443202366431554,
"max": 0.18791091131667295,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.68384877208333e-06,
"min": 3.68384877208333e-06,
"max": 0.0002952807015731,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.105154631624999e-05,
"min": 1.105154631624999e-05,
"max": 0.00084381766872745,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10122791666666665,
"min": 0.10122791666666665,
"max": 0.19842689999999996,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30368375,
"min": 0.20760975000000004,
"max": 0.58127255,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.127304166666664e-05,
"min": 7.127304166666664e-05,
"max": 0.004921502310000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021381912499999993,
"min": 0.00021381912499999993,
"max": 0.014065500245,
"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": "1703727130",
"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": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1703729763"
},
"total": 2633.2940846409997,
"count": 1,
"self": 0.5012580629995682,
"children": {
"run_training.setup": {
"total": 0.05879272099991795,
"count": 1,
"self": 0.05879272099991795
},
"TrainerController.start_learning": {
"total": 2632.734033857,
"count": 1,
"self": 4.669789720928748,
"children": {
"TrainerController._reset_env": {
"total": 3.1299066739998125,
"count": 1,
"self": 3.1299066739998125
},
"TrainerController.advance": {
"total": 2624.808994728072,
"count": 232913,
"self": 5.202662790068189,
"children": {
"env_step": {
"total": 2080.4623251249586,
"count": 232913,
"self": 1728.8492371501843,
"children": {
"SubprocessEnvManager._take_step": {
"total": 348.42508616797295,
"count": 232913,
"self": 17.715936785153417,
"children": {
"TorchPolicy.evaluate": {
"total": 330.70914938281953,
"count": 223023,
"self": 330.70914938281953
}
}
},
"workers": {
"total": 3.188001806801367,
"count": 232913,
"self": 0.0,
"children": {
"worker_root": {
"total": 2625.0481555960178,
"count": 232913,
"is_parallel": true,
"self": 1225.2526956829065,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0007630589998370851,
"count": 1,
"is_parallel": true,
"self": 0.00024945099971773743,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005136080001193477,
"count": 2,
"is_parallel": true,
"self": 0.0005136080001193477
}
}
},
"UnityEnvironment.step": {
"total": 0.03313118400001258,
"count": 1,
"is_parallel": true,
"self": 0.000340128000061668,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002074120000088442,
"count": 1,
"is_parallel": true,
"self": 0.0002074120000088442
},
"communicator.exchange": {
"total": 0.031849550000060844,
"count": 1,
"is_parallel": true,
"self": 0.031849550000060844
},
"steps_from_proto": {
"total": 0.0007340939998812246,
"count": 1,
"is_parallel": true,
"self": 0.00020054199990227062,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000533551999978954,
"count": 2,
"is_parallel": true,
"self": 0.000533551999978954
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1399.7954599131112,
"count": 232912,
"is_parallel": true,
"self": 43.11571185403636,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 92.35216493391454,
"count": 232912,
"is_parallel": true,
"self": 92.35216493391454
},
"communicator.exchange": {
"total": 1166.5666735710988,
"count": 232912,
"is_parallel": true,
"self": 1166.5666735710988
},
"steps_from_proto": {
"total": 97.76090955406153,
"count": 232912,
"is_parallel": true,
"self": 36.65847472427731,
"children": {
"_process_rank_one_or_two_observation": {
"total": 61.102434829784215,
"count": 465824,
"is_parallel": true,
"self": 61.102434829784215
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 539.144006813045,
"count": 232913,
"self": 7.082417171119914,
"children": {
"process_trajectory": {
"total": 168.54527700592485,
"count": 232913,
"self": 167.31556978992444,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2297072160004063,
"count": 10,
"self": 1.2297072160004063
}
}
},
"_update_policy": {
"total": 363.5163126360003,
"count": 97,
"self": 297.9624594980098,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.55385313799047,
"count": 2910,
"self": 65.55385313799047
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0289995771017857e-06,
"count": 1,
"self": 1.0289995771017857e-06
},
"TrainerController._save_models": {
"total": 0.1253417050002099,
"count": 1,
"self": 0.0024311580000357935,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12291054700017412,
"count": 1,
"self": 0.12291054700017412
}
}
}
}
}
}
}