ppo-Huggy / run_logs /timers.json
jsl28's picture
Huggy
96fe4d9
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4041311740875244,
"min": 1.4041311740875244,
"max": 1.4248353242874146,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70601.1171875,
"min": 68841.484375,
"max": 76812.9765625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 83.32546374367622,
"min": 77.14084507042253,
"max": 422.26050420168065,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49412.0,
"min": 48891.0,
"max": 50249.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999955.0,
"min": 49904.0,
"max": 1999955.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999955.0,
"min": 49904.0,
"max": 1999955.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4683613777160645,
"min": 0.03520786017179489,
"max": 2.505298137664795,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1463.73828125,
"min": 4.15452766418457,
"max": 1540.6971435546875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.838623730066856,
"min": 1.759974092876507,
"max": 4.037911519714834,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2276.3038719296455,
"min": 207.67694295942783,
"max": 2470.8575209379196,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.838623730066856,
"min": 1.759974092876507,
"max": 4.037911519714834,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2276.3038719296455,
"min": 207.67694295942783,
"max": 2470.8575209379196,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017125295078585623,
"min": 0.01343819958625924,
"max": 0.02073059611607783,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05137588523575687,
"min": 0.02687639917251848,
"max": 0.06219178834823348,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06535842538707787,
"min": 0.023722916593154272,
"max": 0.06535842538707787,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1960752761612336,
"min": 0.047445833186308545,
"max": 0.1960752761612336,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.642148785983331e-06,
"min": 3.642148785983331e-06,
"max": 0.00029535360154879997,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0926446357949993e-05,
"min": 1.0926446357949993e-05,
"max": 0.0008443044185651999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10121401666666664,
"min": 0.10121401666666664,
"max": 0.1984512,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30364204999999994,
"min": 0.20761470000000004,
"max": 0.5814347999999998,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.057943166666663e-05,
"min": 7.057943166666663e-05,
"max": 0.00492271488,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002117382949999999,
"min": 0.0002117382949999999,
"max": 0.014073596520000002,
"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": "1701215034",
"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": "1701217636"
},
"total": 2602.402285487,
"count": 1,
"self": 0.7833809369999472,
"children": {
"run_training.setup": {
"total": 0.060468280000009145,
"count": 1,
"self": 0.060468280000009145
},
"TrainerController.start_learning": {
"total": 2601.55843627,
"count": 1,
"self": 4.790602276993013,
"children": {
"TrainerController._reset_env": {
"total": 3.347274721999952,
"count": 1,
"self": 3.347274721999952
},
"TrainerController.advance": {
"total": 2593.2671854450073,
"count": 232791,
"self": 5.473460572954991,
"children": {
"env_step": {
"total": 2058.088040327062,
"count": 232791,
"self": 1699.7487259429886,
"children": {
"SubprocessEnvManager._take_step": {
"total": 355.06648093804307,
"count": 232791,
"self": 17.955346806137754,
"children": {
"TorchPolicy.evaluate": {
"total": 337.1111341319053,
"count": 222920,
"self": 337.1111341319053
}
}
},
"workers": {
"total": 3.2728334460305177,
"count": 232791,
"self": 0.0,
"children": {
"worker_root": {
"total": 2593.443672356986,
"count": 232791,
"is_parallel": true,
"self": 1219.9872135550868,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008380749999901127,
"count": 1,
"is_parallel": true,
"self": 0.00022490200001357152,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006131729999765412,
"count": 2,
"is_parallel": true,
"self": 0.0006131729999765412
}
}
},
"UnityEnvironment.step": {
"total": 0.030021350000026814,
"count": 1,
"is_parallel": true,
"self": 0.00034693300005983474,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020796600000494436,
"count": 1,
"is_parallel": true,
"self": 0.00020796600000494436
},
"communicator.exchange": {
"total": 0.02863445299999512,
"count": 1,
"is_parallel": true,
"self": 0.02863445299999512
},
"steps_from_proto": {
"total": 0.0008319979999669158,
"count": 1,
"is_parallel": true,
"self": 0.00023614799994220448,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005958500000247113,
"count": 2,
"is_parallel": true,
"self": 0.0005958500000247113
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1373.4564588018993,
"count": 232790,
"is_parallel": true,
"self": 42.12000679476864,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 90.66894317798062,
"count": 232790,
"is_parallel": true,
"self": 90.66894317798062
},
"communicator.exchange": {
"total": 1145.0445916030833,
"count": 232790,
"is_parallel": true,
"self": 1145.0445916030833
},
"steps_from_proto": {
"total": 95.6229172260667,
"count": 232790,
"is_parallel": true,
"self": 35.84869234214386,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.77422488392284,
"count": 465580,
"is_parallel": true,
"self": 59.77422488392284
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 529.7056845449903,
"count": 232791,
"self": 7.3287179319797815,
"children": {
"process_trajectory": {
"total": 169.823555025009,
"count": 232791,
"self": 168.54012547400896,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2834295510000402,
"count": 10,
"self": 1.2834295510000402
}
}
},
"_update_policy": {
"total": 352.5534115880015,
"count": 97,
"self": 287.5265875910226,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.02682399697892,
"count": 2910,
"self": 65.02682399697892
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2900000001536682e-06,
"count": 1,
"self": 1.2900000001536682e-06
},
"TrainerController._save_models": {
"total": 0.15337253600000622,
"count": 1,
"self": 0.0028511489999800688,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15052138700002615,
"count": 1,
"self": 0.15052138700002615
}
}
}
}
}
}
}