ppo-Huggy / run_logs /timers.json
Xxmlala's picture
Huggy
02a09e3
raw
history blame
17.4 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3990815877914429,
"min": 1.3990815877914429,
"max": 1.4268224239349365,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69478.390625,
"min": 69125.6171875,
"max": 76601.0546875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 74.66515151515152,
"min": 67.57260273972602,
"max": 393.5,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49279.0,
"min": 49104.0,
"max": 50368.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999948.0,
"min": 49835.0,
"max": 1999948.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999948.0,
"min": 49835.0,
"max": 1999948.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.5091183185577393,
"min": -0.07920075207948685,
"max": 2.5579800605773926,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1656.01806640625,
"min": -10.05849552154541,
"max": 1793.5859375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.956576590194847,
"min": 1.8321487971647519,
"max": 4.144638768138265,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2611.340549528599,
"min": 232.68289723992348,
"max": 2864.4712904691696,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.956576590194847,
"min": 1.8321487971647519,
"max": 4.144638768138265,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2611.340549528599,
"min": 232.68289723992348,
"max": 2864.4712904691696,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.0160146458724436,
"min": 0.01255478299766158,
"max": 0.020452227007545946,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.048043937617330806,
"min": 0.02510956599532316,
"max": 0.06135668102263784,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05813503770364656,
"min": 0.024187326710671187,
"max": 0.06411827728152275,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17440511311093967,
"min": 0.048374653421342374,
"max": 0.18415279934803644,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.025048658349993e-06,
"min": 4.025048658349993e-06,
"max": 0.0002952987015670999,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.2075145975049979e-05,
"min": 1.2075145975049979e-05,
"max": 0.00084420466859845,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10134164999999999,
"min": 0.10134164999999999,
"max": 0.19843290000000008,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30402494999999996,
"min": 0.2078164,
"max": 0.5814015500000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.694833499999992e-05,
"min": 7.694833499999992e-05,
"max": 0.00492180171,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00023084500499999977,
"min": 0.00023084500499999977,
"max": 0.014071937345,
"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": "1689419961",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
"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": "1689422460"
},
"total": 2498.2227836479997,
"count": 1,
"self": 0.44425647699972615,
"children": {
"run_training.setup": {
"total": 0.043582487000008996,
"count": 1,
"self": 0.043582487000008996
},
"TrainerController.start_learning": {
"total": 2497.734944684,
"count": 1,
"self": 4.500941999041515,
"children": {
"TrainerController._reset_env": {
"total": 4.281982357000004,
"count": 1,
"self": 4.281982357000004
},
"TrainerController.advance": {
"total": 2488.832668967958,
"count": 233371,
"self": 4.565594480890468,
"children": {
"env_step": {
"total": 1925.344339500011,
"count": 233371,
"self": 1625.7107883730323,
"children": {
"SubprocessEnvManager._take_step": {
"total": 296.78645331600865,
"count": 233371,
"self": 17.185320669977045,
"children": {
"TorchPolicy.evaluate": {
"total": 279.6011326460316,
"count": 222904,
"self": 279.6011326460316
}
}
},
"workers": {
"total": 2.84709781097024,
"count": 233371,
"self": 0.0,
"children": {
"worker_root": {
"total": 2490.0724339629596,
"count": 233371,
"is_parallel": true,
"self": 1156.5688681699555,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010212149999802023,
"count": 1,
"is_parallel": true,
"self": 0.0002787009999849488,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007425139999952535,
"count": 2,
"is_parallel": true,
"self": 0.0007425139999952535
}
}
},
"UnityEnvironment.step": {
"total": 0.029744931999999835,
"count": 1,
"is_parallel": true,
"self": 0.0003466149999837853,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00025617700001134835,
"count": 1,
"is_parallel": true,
"self": 0.00025617700001134835
},
"communicator.exchange": {
"total": 0.028396377000007078,
"count": 1,
"is_parallel": true,
"self": 0.028396377000007078
},
"steps_from_proto": {
"total": 0.0007457629999976234,
"count": 1,
"is_parallel": true,
"self": 0.00018954399996573557,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005562190000318878,
"count": 2,
"is_parallel": true,
"self": 0.0005562190000318878
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1333.503565793004,
"count": 233370,
"is_parallel": true,
"self": 41.21444344822157,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.01560711690982,
"count": 233370,
"is_parallel": true,
"self": 82.01560711690982
},
"communicator.exchange": {
"total": 1110.2987324969565,
"count": 233370,
"is_parallel": true,
"self": 1110.2987324969565
},
"steps_from_proto": {
"total": 99.97478273091608,
"count": 233370,
"is_parallel": true,
"self": 35.2776477849018,
"children": {
"_process_rank_one_or_two_observation": {
"total": 64.69713494601427,
"count": 466740,
"is_parallel": true,
"self": 64.69713494601427
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 558.9227349870566,
"count": 233371,
"self": 6.597085273022003,
"children": {
"process_trajectory": {
"total": 144.14728423103531,
"count": 233371,
"self": 142.54061074203463,
"children": {
"RLTrainer._checkpoint": {
"total": 1.6066734890006842,
"count": 10,
"self": 1.6066734890006842
}
}
},
"_update_policy": {
"total": 408.1783654829993,
"count": 97,
"self": 346.76571215599205,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.41265332700726,
"count": 2910,
"self": 61.41265332700726
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.22000253922306e-07,
"count": 1,
"self": 9.22000253922306e-07
},
"TrainerController._save_models": {
"total": 0.11935043800031053,
"count": 1,
"self": 0.0019483370001580624,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11740210100015247,
"count": 1,
"self": 0.11740210100015247
}
}
}
}
}
}
}