ppo-Huggy / run_logs /timers.json
startlightquyet's picture
Huggy
34c6694
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4060425758361816,
"min": 1.4060425758361816,
"max": 1.4291889667510986,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69995.609375,
"min": 67013.5,
"max": 78992.53125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 121.27073170731707,
"min": 94.53537284894837,
"max": 395.98425196850394,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49721.0,
"min": 48858.0,
"max": 50290.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999998.0,
"min": 49839.0,
"max": 1999998.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999998.0,
"min": 49839.0,
"max": 1999998.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.253486156463623,
"min": 0.11108647286891937,
"max": 2.363626480102539,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 923.9293212890625,
"min": 13.996895790100098,
"max": 1220.8853759765625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.4545266299712947,
"min": 1.729396685484856,
"max": 3.833172809979147,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1416.355918288231,
"min": 217.90398237109184,
"max": 1879.814623773098,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.4545266299712947,
"min": 1.729396685484856,
"max": 3.833172809979147,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1416.355918288231,
"min": 217.90398237109184,
"max": 1879.814623773098,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.019544873487150956,
"min": 0.01260775118280435,
"max": 0.020451930616400202,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03908974697430191,
"min": 0.0252155023656087,
"max": 0.05559918590976547,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04431684066851933,
"min": 0.021975165170927843,
"max": 0.05888005637874206,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.08863368133703867,
"min": 0.043950330341855685,
"max": 0.17091136015951633,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.499273500275005e-06,
"min": 4.499273500275005e-06,
"max": 0.00029533740155420006,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.99854700055001e-06,
"min": 8.99854700055001e-06,
"max": 0.0008441895186035001,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10149972500000001,
"min": 0.10149972500000001,
"max": 0.1984458,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20299945000000003,
"min": 0.20299945000000003,
"max": 0.5813965000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.48362775000001e-05,
"min": 8.48362775000001e-05,
"max": 0.004922445420000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001696725550000002,
"min": 0.0001696725550000002,
"max": 0.014071685349999998,
"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": "1699926783",
"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": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1699929396"
},
"total": 2613.496686847,
"count": 1,
"self": 0.8091158199999882,
"children": {
"run_training.setup": {
"total": 0.06949303600003987,
"count": 1,
"self": 0.06949303600003987
},
"TrainerController.start_learning": {
"total": 2612.618077991,
"count": 1,
"self": 4.680283482889081,
"children": {
"TrainerController._reset_env": {
"total": 8.743889722000006,
"count": 1,
"self": 8.743889722000006
},
"TrainerController.advance": {
"total": 2599.0458045981104,
"count": 230914,
"self": 4.999058413176499,
"children": {
"env_step": {
"total": 2078.741579788879,
"count": 230914,
"self": 1708.818093025838,
"children": {
"SubprocessEnvManager._take_step": {
"total": 366.8157886719952,
"count": 230914,
"self": 17.668369911946684,
"children": {
"TorchPolicy.evaluate": {
"total": 349.14741876004854,
"count": 222940,
"self": 349.14741876004854
}
}
},
"workers": {
"total": 3.1076980910457337,
"count": 230914,
"self": 0.0,
"children": {
"worker_root": {
"total": 2604.795817377991,
"count": 230914,
"is_parallel": true,
"self": 1221.754733546996,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001009738999982801,
"count": 1,
"is_parallel": true,
"self": 0.00032676599994374556,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006829730000390555,
"count": 2,
"is_parallel": true,
"self": 0.0006829730000390555
}
}
},
"UnityEnvironment.step": {
"total": 0.030392532000007577,
"count": 1,
"is_parallel": true,
"self": 0.0003683469999486988,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00024252800000112984,
"count": 1,
"is_parallel": true,
"self": 0.00024252800000112984
},
"communicator.exchange": {
"total": 0.02892228400003205,
"count": 1,
"is_parallel": true,
"self": 0.02892228400003205
},
"steps_from_proto": {
"total": 0.0008593730000256983,
"count": 1,
"is_parallel": true,
"self": 0.00024432600002910476,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006150469999965935,
"count": 2,
"is_parallel": true,
"self": 0.0006150469999965935
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1383.0410838309951,
"count": 230913,
"is_parallel": true,
"self": 41.27521654206316,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 91.18078388797556,
"count": 230913,
"is_parallel": true,
"self": 91.18078388797556
},
"communicator.exchange": {
"total": 1156.3106686999092,
"count": 230913,
"is_parallel": true,
"self": 1156.3106686999092
},
"steps_from_proto": {
"total": 94.27441470104714,
"count": 230913,
"is_parallel": true,
"self": 35.55455276598968,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.71986193505745,
"count": 461826,
"is_parallel": true,
"self": 58.71986193505745
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 515.305166396055,
"count": 230914,
"self": 7.024643890048367,
"children": {
"process_trajectory": {
"total": 159.7377171860045,
"count": 230914,
"self": 158.43226052100363,
"children": {
"RLTrainer._checkpoint": {
"total": 1.305456665000861,
"count": 10,
"self": 1.305456665000861
}
}
},
"_update_policy": {
"total": 348.5428053200022,
"count": 96,
"self": 285.3584398730096,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.18436544699256,
"count": 2880,
"self": 63.18436544699256
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.6080002751550637e-06,
"count": 1,
"self": 1.6080002751550637e-06
},
"TrainerController._save_models": {
"total": 0.14809858000035092,
"count": 1,
"self": 0.0026624580004863674,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14543612199986455,
"count": 1,
"self": 0.14543612199986455
}
}
}
}
}
}
}