ppo-PyramidsRND / run_logs /timers.json
alesthehuman's picture
First Push
befca33
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.13963830471038818,
"min": 0.1354147344827652,
"max": 1.3859013319015503,
"count": 100
},
"Pyramids.Policy.Entropy.sum": {
"value": 4198.0859375,
"min": 4066.775390625,
"max": 42042.703125,
"count": 100
},
"Pyramids.Step.mean": {
"value": 2999927.0,
"min": 29874.0,
"max": 2999927.0,
"count": 100
},
"Pyramids.Step.sum": {
"value": 2999927.0,
"min": 29874.0,
"max": 2999927.0,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.7461395263671875,
"min": -0.09502255916595459,
"max": 0.8830022811889648,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 221.6034393310547,
"min": -22.900436401367188,
"max": 275.4967041015625,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.011884202249348164,
"min": -0.023134874179959297,
"max": 0.5487221479415894,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 3.5296080112457275,
"min": -6.685978412628174,
"max": 130.04714965820312,
"count": 100
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06774965975071408,
"min": 0.06256368778122125,
"max": 0.07352444409313642,
"count": 100
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0162448962607111,
"min": 0.4923342106520632,
"max": 1.0888277028003392,
"count": 100
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.013757862352455658,
"min": 0.0005655370779689311,
"max": 0.01876064310303931,
"count": 100
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.20636793528683486,
"min": 0.007351982013596103,
"max": 0.2626490034425503,
"count": 100
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.488246170617772e-06,
"min": 1.488246170617772e-06,
"max": 0.00029841208624359046,
"count": 100
},
"Pyramids.Policy.LearningRate.sum": {
"value": 2.232369255926658e-05,
"min": 2.232369255926658e-05,
"max": 0.0040109192630269335,
"count": 100
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10049604888888888,
"min": 0.10049604888888888,
"max": 0.19947069523809527,
"count": 100
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5074407333333333,
"min": 1.3962948666666668,
"max": 2.752357866666667,
"count": 100
},
"Pyramids.Policy.Beta.mean": {
"value": 5.9555283999999795e-05,
"min": 5.9555283999999795e-05,
"max": 0.009947122454285712,
"count": 100
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0008933292599999969,
"min": 0.0008933292599999969,
"max": 0.13370360936,
"count": 100
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.007588631473481655,
"min": 0.007429925259202719,
"max": 0.5717369914054871,
"count": 100
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.11382947117090225,
"min": 0.10401895642280579,
"max": 4.002159118652344,
"count": 100
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 246.2357723577236,
"min": 197.43046357615893,
"max": 997.375,
"count": 100
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30287.0,
"min": 16545.0,
"max": 32790.0,
"count": 100
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7212390081911553,
"min": -0.926487551536411,
"max": 1.789269488436956,
"count": 100
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 211.7123980075121,
"min": -29.647601649165154,
"max": 268.18719789385796,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7212390081911553,
"min": -0.926487551536411,
"max": 1.789269488436956,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 211.7123980075121,
"min": -29.647601649165154,
"max": 268.18719789385796,
"count": 100
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.01946287985398468,
"min": 0.015993219603167998,
"max": 10.994168645318817,
"count": 100
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.393934222040116,
"min": 2.1327608428728126,
"max": 186.90086697041988,
"count": 100
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1688066279",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn --force ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --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": "1688073875"
},
"total": 7595.869846178997,
"count": 1,
"self": 0.488449373999174,
"children": {
"run_training.setup": {
"total": 0.038548343000002205,
"count": 1,
"self": 0.038548343000002205
},
"TrainerController.start_learning": {
"total": 7595.342848461998,
"count": 1,
"self": 4.052116816743364,
"children": {
"TrainerController._reset_env": {
"total": 5.210483083999861,
"count": 1,
"self": 5.210483083999861
},
"TrainerController.advance": {
"total": 7585.980297503254,
"count": 195034,
"self": 4.186577750144352,
"children": {
"env_step": {
"total": 5629.625360692509,
"count": 195034,
"self": 5301.945797727247,
"children": {
"SubprocessEnvManager._take_step": {
"total": 325.30831228856186,
"count": 195034,
"self": 14.034539667623903,
"children": {
"TorchPolicy.evaluate": {
"total": 311.27377262093796,
"count": 187562,
"self": 311.27377262093796
}
}
},
"workers": {
"total": 2.3712506767005834,
"count": 195034,
"self": 0.0,
"children": {
"worker_root": {
"total": 7578.586230859193,
"count": 195034,
"is_parallel": true,
"self": 2631.188546249985,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0018521640013204888,
"count": 1,
"is_parallel": true,
"self": 0.0005657699985022191,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012863940028182697,
"count": 8,
"is_parallel": true,
"self": 0.0012863940028182697
}
}
},
"UnityEnvironment.step": {
"total": 0.10076710599969374,
"count": 1,
"is_parallel": true,
"self": 0.0005620769989036489,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005008580010326114,
"count": 1,
"is_parallel": true,
"self": 0.0005008580010326114
},
"communicator.exchange": {
"total": 0.0978270240011625,
"count": 1,
"is_parallel": true,
"self": 0.0978270240011625
},
"steps_from_proto": {
"total": 0.0018771469985949807,
"count": 1,
"is_parallel": true,
"self": 0.00040593399535282515,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014712130032421555,
"count": 8,
"is_parallel": true,
"self": 0.0014712130032421555
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 4947.397684609208,
"count": 195033,
"is_parallel": true,
"self": 102.16493539073781,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 66.93418035602372,
"count": 195033,
"is_parallel": true,
"self": 66.93418035602372
},
"communicator.exchange": {
"total": 4473.237247137615,
"count": 195033,
"is_parallel": true,
"self": 4473.237247137615
},
"steps_from_proto": {
"total": 305.06132172483194,
"count": 195033,
"is_parallel": true,
"self": 59.931892875032645,
"children": {
"_process_rank_one_or_two_observation": {
"total": 245.1294288497993,
"count": 1560264,
"is_parallel": true,
"self": 245.1294288497993
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1952.1683590606008,
"count": 195034,
"self": 7.915415505856799,
"children": {
"process_trajectory": {
"total": 333.94870120070846,
"count": 195034,
"self": 333.296986995716,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6517142049924587,
"count": 6,
"self": 0.6517142049924587
}
}
},
"_update_policy": {
"total": 1610.3042423540355,
"count": 1402,
"self": 1031.6672738925663,
"children": {
"TorchPPOOptimizer.update": {
"total": 578.6369684614692,
"count": 68337,
"self": 578.6369684614692
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0000003385357559e-06,
"count": 1,
"self": 1.0000003385357559e-06
},
"TrainerController._save_models": {
"total": 0.09995005800010404,
"count": 1,
"self": 0.0019889360009983648,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09796112199910567,
"count": 1,
"self": 0.09796112199910567
}
}
}
}
}
}
}