ppo-Huggy / run_logs /timers.json
mobydoby's picture
Huggy
135fe66 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4045722484588623,
"min": 1.404556393623352,
"max": 1.4271043539047241,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69040.34375,
"min": 67857.0859375,
"max": 76854.375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 85.5484429065744,
"min": 80.75777414075286,
"max": 406.3709677419355,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49447.0,
"min": 49145.0,
"max": 50390.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999945.0,
"min": 49898.0,
"max": 1999945.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999945.0,
"min": 49898.0,
"max": 1999945.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4473636150360107,
"min": 0.07192805409431458,
"max": 2.4626667499542236,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1414.576171875,
"min": 8.847150802612305,
"max": 1488.697265625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8492975772252134,
"min": 1.915912222329194,
"max": 3.927365542785135,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2224.8939996361732,
"min": 235.65720334649086,
"max": 2297.1662835478783,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8492975772252134,
"min": 1.915912222329194,
"max": 3.927365542785135,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2224.8939996361732,
"min": 235.65720334649086,
"max": 2297.1662835478783,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017303386799418754,
"min": 0.013953447333036214,
"max": 0.02126827456061922,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.051910160398256265,
"min": 0.027906894666072428,
"max": 0.056261072231185,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.052421192990409,
"min": 0.021426658425480125,
"max": 0.05819613598287106,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.157263578971227,
"min": 0.04285331685096025,
"max": 0.1714778655519088,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.4902488366166702e-06,
"min": 3.4902488366166702e-06,
"max": 0.0002952767265744249,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.047074650985001e-05,
"min": 1.047074650985001e-05,
"max": 0.0008439652686782501,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10116338333333337,
"min": 0.10116338333333337,
"max": 0.198425575,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3034901500000001,
"min": 0.20746439999999994,
"max": 0.58132175,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.805282833333341e-05,
"min": 6.805282833333341e-05,
"max": 0.004921436192500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020415848500000022,
"min": 0.00020415848500000022,
"max": 0.014067955325,
"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": "1706111290",
"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 --force",
"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": "1706113765"
},
"total": 2475.656316673,
"count": 1,
"self": 0.44225634499980515,
"children": {
"run_training.setup": {
"total": 0.04627686800040465,
"count": 1,
"self": 0.04627686800040465
},
"TrainerController.start_learning": {
"total": 2475.16778346,
"count": 1,
"self": 4.63316434098715,
"children": {
"TrainerController._reset_env": {
"total": 3.2929726129996197,
"count": 1,
"self": 3.2929726129996197
},
"TrainerController.advance": {
"total": 2467.1206817550137,
"count": 232387,
"self": 4.812261282132567,
"children": {
"env_step": {
"total": 1978.3066770718183,
"count": 232387,
"self": 1643.7584562867733,
"children": {
"SubprocessEnvManager._take_step": {
"total": 331.55275366390606,
"count": 232387,
"self": 16.723647483760942,
"children": {
"TorchPolicy.evaluate": {
"total": 314.8291061801451,
"count": 222880,
"self": 314.8291061801451
}
}
},
"workers": {
"total": 2.9954671211389723,
"count": 232387,
"self": 0.0,
"children": {
"worker_root": {
"total": 2467.6375195261403,
"count": 232387,
"is_parallel": true,
"self": 1125.0020323070607,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008040669999900274,
"count": 1,
"is_parallel": true,
"self": 0.00019913699998141965,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006049300000086077,
"count": 2,
"is_parallel": true,
"self": 0.0006049300000086077
}
}
},
"UnityEnvironment.step": {
"total": 0.030003931999999622,
"count": 1,
"is_parallel": true,
"self": 0.0003735120003511838,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023909199990157504,
"count": 1,
"is_parallel": true,
"self": 0.00023909199990157504
},
"communicator.exchange": {
"total": 0.028595976999895356,
"count": 1,
"is_parallel": true,
"self": 0.028595976999895356
},
"steps_from_proto": {
"total": 0.0007953509998515074,
"count": 1,
"is_parallel": true,
"self": 0.00022685600015392993,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005684949996975774,
"count": 2,
"is_parallel": true,
"self": 0.0005684949996975774
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1342.6354872190796,
"count": 232386,
"is_parallel": true,
"self": 42.383247560234395,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 86.63245696298827,
"count": 232386,
"is_parallel": true,
"self": 86.63245696298827
},
"communicator.exchange": {
"total": 1119.336582034925,
"count": 232386,
"is_parallel": true,
"self": 1119.336582034925
},
"steps_from_proto": {
"total": 94.28320066093193,
"count": 232386,
"is_parallel": true,
"self": 33.32838424908505,
"children": {
"_process_rank_one_or_two_observation": {
"total": 60.95481641184688,
"count": 464772,
"is_parallel": true,
"self": 60.95481641184688
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 484.00174340106287,
"count": 232387,
"self": 7.211990955175224,
"children": {
"process_trajectory": {
"total": 155.48126750689062,
"count": 232387,
"self": 154.27316288088969,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2081046260009316,
"count": 10,
"self": 1.2081046260009316
}
}
},
"_update_policy": {
"total": 321.308484938997,
"count": 97,
"self": 257.26002820901294,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.04845672998408,
"count": 2910,
"self": 64.04845672998408
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.379991752211936e-07,
"count": 1,
"self": 9.379991752211936e-07
},
"TrainerController._save_models": {
"total": 0.12096381300034409,
"count": 1,
"self": 0.002104793000398786,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1188590199999453,
"count": 1,
"self": 0.1188590199999453
}
}
}
}
}
}
}