ppo-Pyramids / run_logs /timers.json
gsotnikov's picture
First Push
c4e0f01
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5105369687080383,
"min": 0.5036460161209106,
"max": 1.4236077070236206,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 15283.435546875,
"min": 15198.0224609375,
"max": 43186.5625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989976.0,
"min": 29910.0,
"max": 989976.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989976.0,
"min": 29910.0,
"max": 989976.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.463505357503891,
"min": -0.0985526517033577,
"max": 0.579032838344574,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 122.82891845703125,
"min": -23.849740982055664,
"max": 160.39208984375,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.005613792221993208,
"min": -0.005613792221993208,
"max": 0.4639880955219269,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -1.4876549243927002,
"min": -1.4876549243927002,
"max": 110.42916870117188,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06573412623783086,
"min": 0.062164827000198514,
"max": 0.07485746090262554,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9202777673296321,
"min": 0.5089814201821627,
"max": 1.0716112161473441,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01222862632407452,
"min": 0.00015194079621619428,
"max": 0.022014564295086782,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.17120076853704327,
"min": 0.00212717114702672,
"max": 0.21633931594117833,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.293418997464285e-06,
"min": 7.293418997464285e-06,
"max": 0.0002952347158741428,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010210786596449998,
"min": 0.00010210786596449998,
"max": 0.0037582300472566994,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10243110714285712,
"min": 0.10243110714285712,
"max": 0.19841157142857144,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4340354999999998,
"min": 1.388881,
"max": 2.652743300000001,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025286760357142856,
"min": 0.00025286760357142856,
"max": 0.009841315985714286,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.00354014645,
"min": 0.00354014645,
"max": 0.12528905567,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.01000965852290392,
"min": 0.01000965852290392,
"max": 0.8042423129081726,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.14013521373271942,
"min": 0.14013521373271942,
"max": 5.629696369171143,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 418.972602739726,
"min": 337.1666666666667,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30585.0,
"min": 17220.0,
"max": 34217.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.4165753212897745,
"min": -0.9998645686334179,
"max": 1.6047276939792805,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 103.40999845415354,
"min": -30.995801627635956,
"max": 134.79239797592163,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.4165753212897745,
"min": -0.9998645686334179,
"max": 1.6047276939792805,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 103.40999845415354,
"min": -30.995801627635956,
"max": 134.79239797592163,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.043465900572362895,
"min": 0.03739372393604191,
"max": 15.617709757139286,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.173010741782491,
"min": 3.139557426155079,
"max": 281.11877562850714,
"count": 33
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1685098829",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./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": "1685101013"
},
"total": 2184.403781973,
"count": 1,
"self": 0.7300603550002052,
"children": {
"run_training.setup": {
"total": 0.05704740600003788,
"count": 1,
"self": 0.05704740600003788
},
"TrainerController.start_learning": {
"total": 2183.616674212,
"count": 1,
"self": 1.5618220420224134,
"children": {
"TrainerController._reset_env": {
"total": 4.859687903999884,
"count": 1,
"self": 4.859687903999884
},
"TrainerController.advance": {
"total": 2177.054907620978,
"count": 63782,
"self": 1.5181805268935022,
"children": {
"env_step": {
"total": 1540.147259158008,
"count": 63782,
"self": 1425.3233293779497,
"children": {
"SubprocessEnvManager._take_step": {
"total": 113.94927005801901,
"count": 63782,
"self": 4.90253527408322,
"children": {
"TorchPolicy.evaluate": {
"total": 109.04673478393579,
"count": 62540,
"self": 109.04673478393579
}
}
},
"workers": {
"total": 0.8746597220392687,
"count": 63782,
"self": 0.0,
"children": {
"worker_root": {
"total": 2178.1532643149876,
"count": 63782,
"is_parallel": true,
"self": 870.4380461489536,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0024616809998860845,
"count": 1,
"is_parallel": true,
"self": 0.0006885099999180966,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017731709999679879,
"count": 8,
"is_parallel": true,
"self": 0.0017731709999679879
}
}
},
"UnityEnvironment.step": {
"total": 0.04664487900004133,
"count": 1,
"is_parallel": true,
"self": 0.0005728589999307587,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005626000001939246,
"count": 1,
"is_parallel": true,
"self": 0.0005626000001939246
},
"communicator.exchange": {
"total": 0.04363360299998931,
"count": 1,
"is_parallel": true,
"self": 0.04363360299998931
},
"steps_from_proto": {
"total": 0.0018758169999273377,
"count": 1,
"is_parallel": true,
"self": 0.0004097670000646758,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001466049999862662,
"count": 8,
"is_parallel": true,
"self": 0.001466049999862662
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1307.715218166034,
"count": 63781,
"is_parallel": true,
"self": 32.28947026296123,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.94012055902067,
"count": 63781,
"is_parallel": true,
"self": 22.94012055902067
},
"communicator.exchange": {
"total": 1152.960599951089,
"count": 63781,
"is_parallel": true,
"self": 1152.960599951089
},
"steps_from_proto": {
"total": 99.52502739296301,
"count": 63781,
"is_parallel": true,
"self": 20.57901701979813,
"children": {
"_process_rank_one_or_two_observation": {
"total": 78.94601037316488,
"count": 510248,
"is_parallel": true,
"self": 78.94601037316488
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 635.3894679360767,
"count": 63782,
"self": 2.806349684015686,
"children": {
"process_trajectory": {
"total": 108.4374069840585,
"count": 63782,
"self": 108.13967482705834,
"children": {
"RLTrainer._checkpoint": {
"total": 0.297732157000155,
"count": 2,
"self": 0.297732157000155
}
}
},
"_update_policy": {
"total": 524.1457112680025,
"count": 457,
"self": 339.4933938170245,
"children": {
"TorchPPOOptimizer.update": {
"total": 184.652317450978,
"count": 22824,
"self": 184.652317450978
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2249997780600097e-06,
"count": 1,
"self": 1.2249997780600097e-06
},
"TrainerController._save_models": {
"total": 0.1402554199999031,
"count": 1,
"self": 0.0019310479997329821,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13832437200017011,
"count": 1,
"self": 0.13832437200017011
}
}
}
}
}
}
}