ppo-Huggy / run_logs /timers.json
rmpmalheiro's picture
Huggy
7720e6f
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.408457636833191,
"min": 1.408457636833191,
"max": 1.4285295009613037,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69898.9375,
"min": 68169.5078125,
"max": 78758.671875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 85.68804159445408,
"min": 73.68310911808669,
"max": 385.61538461538464,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49442.0,
"min": 49284.0,
"max": 50130.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999955.0,
"min": 49510.0,
"max": 1999955.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999955.0,
"min": 49510.0,
"max": 1999955.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.406120538711548,
"min": 0.11321701854467392,
"max": 2.4819459915161133,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1388.33154296875,
"min": 14.604995727539062,
"max": 1628.4991455078125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.664989171346304,
"min": 1.9472681387912396,
"max": 3.998045933942,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2114.6987518668175,
"min": 251.1975899040699,
"max": 2588.775999069214,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.664989171346304,
"min": 1.9472681387912396,
"max": 3.998045933942,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2114.6987518668175,
"min": 251.1975899040699,
"max": 2588.775999069214,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01507258930703554,
"min": 0.012646687519089836,
"max": 0.020473142671759585,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04521776792110662,
"min": 0.026011612693158288,
"max": 0.056442311330465594,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05404496664802233,
"min": 0.021417497439930835,
"max": 0.061584638369580114,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.162134899944067,
"min": 0.04283499487986167,
"max": 0.1807014829168717,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5071988309666635e-06,
"min": 3.5071988309666635e-06,
"max": 0.00029534872655042493,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.052159649289999e-05,
"min": 1.052159649289999e-05,
"max": 0.0008438412187195998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10116903333333334,
"min": 0.10116903333333334,
"max": 0.19844957500000004,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30350710000000003,
"min": 0.20747295000000002,
"max": 0.5812804000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.833476333333327e-05,
"min": 6.833476333333327e-05,
"max": 0.0049226337925000006,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020500428999999982,
"min": 0.00020500428999999982,
"max": 0.014065891960000002,
"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": "1694425895",
"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": "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": "1694428303"
},
"total": 2408.335647167,
"count": 1,
"self": 0.44277322100015226,
"children": {
"run_training.setup": {
"total": 0.044843834999937826,
"count": 1,
"self": 0.044843834999937826
},
"TrainerController.start_learning": {
"total": 2407.848030111,
"count": 1,
"self": 4.422544399037633,
"children": {
"TrainerController._reset_env": {
"total": 4.37274470400007,
"count": 1,
"self": 4.37274470400007
},
"TrainerController.advance": {
"total": 2398.937734171962,
"count": 232712,
"self": 4.515864014036197,
"children": {
"env_step": {
"total": 1865.1882228799202,
"count": 232712,
"self": 1579.6815411007947,
"children": {
"SubprocessEnvManager._take_step": {
"total": 282.63539580608335,
"count": 232712,
"self": 16.53538608904273,
"children": {
"TorchPolicy.evaluate": {
"total": 266.1000097170406,
"count": 222970,
"self": 266.1000097170406
}
}
},
"workers": {
"total": 2.871285973042177,
"count": 232712,
"self": 0.0,
"children": {
"worker_root": {
"total": 2400.3138680559023,
"count": 232712,
"is_parallel": true,
"self": 1107.317917063929,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009192210000037448,
"count": 1,
"is_parallel": true,
"self": 0.00022003499998390907,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006991860000198358,
"count": 2,
"is_parallel": true,
"self": 0.0006991860000198358
}
}
},
"UnityEnvironment.step": {
"total": 0.044832772000063414,
"count": 1,
"is_parallel": true,
"self": 0.000331661000245731,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00024063899991233484,
"count": 1,
"is_parallel": true,
"self": 0.00024063899991233484
},
"communicator.exchange": {
"total": 0.04355729300004896,
"count": 1,
"is_parallel": true,
"self": 0.04355729300004896
},
"steps_from_proto": {
"total": 0.0007031789998563909,
"count": 1,
"is_parallel": true,
"self": 0.00020751299985022342,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004956660000061675,
"count": 2,
"is_parallel": true,
"self": 0.0004956660000061675
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1292.9959509919734,
"count": 232711,
"is_parallel": true,
"self": 40.04803440100909,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.5728906689692,
"count": 232711,
"is_parallel": true,
"self": 82.5728906689692
},
"communicator.exchange": {
"total": 1070.251773552921,
"count": 232711,
"is_parallel": true,
"self": 1070.251773552921
},
"steps_from_proto": {
"total": 100.12325236907418,
"count": 232711,
"is_parallel": true,
"self": 37.436557613066725,
"children": {
"_process_rank_one_or_two_observation": {
"total": 62.686694756007455,
"count": 465422,
"is_parallel": true,
"self": 62.686694756007455
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 529.2336472780055,
"count": 232712,
"self": 6.253501932878635,
"children": {
"process_trajectory": {
"total": 137.79409989312762,
"count": 232712,
"self": 136.37737356812795,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4167263249996722,
"count": 10,
"self": 1.4167263249996722
}
}
},
"_update_policy": {
"total": 385.18604545199923,
"count": 97,
"self": 327.3486357390025,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.83740971299676,
"count": 2910,
"self": 57.83740971299676
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.410002010350581e-07,
"count": 1,
"self": 8.410002010350581e-07
},
"TrainerController._save_models": {
"total": 0.11500599500004682,
"count": 1,
"self": 0.0019623589996626833,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11304363600038414,
"count": 1,
"self": 0.11304363600038414
}
}
}
}
}
}
}