ppo-Pyramids / run_logs /timers.json
ksanchis's picture
First Push
3369a45
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.4216815233230591,
"min": 0.4216815233230591,
"max": 1.454910159111023,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 12582.9765625,
"min": 12582.9765625,
"max": 44136.15625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989880.0,
"min": 29922.0,
"max": 989880.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989880.0,
"min": 29922.0,
"max": 989880.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.26853451132774353,
"min": -0.10338622331619263,
"max": 0.27540844678878784,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 69.28190612792969,
"min": -24.916080474853516,
"max": 70.77996826171875,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.06056021898984909,
"min": -0.03365710377693176,
"max": 0.35118547081947327,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 15.624536514282227,
"min": -8.616218566894531,
"max": 83.23095703125,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06680221401274182,
"min": 0.06452623149465687,
"max": 0.0724506602843986,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9352309961783856,
"min": 0.4850458411286429,
"max": 1.056299062055426,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.012773293222510673,
"min": 0.0008625350910470761,
"max": 0.013472329138797551,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.17882610511514943,
"min": 0.01121295618361199,
"max": 0.18861260794316573,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.480511792242856e-06,
"min": 7.480511792242856e-06,
"max": 0.0002952342015886,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010472716509139998,
"min": 0.00010472716509139998,
"max": 0.0035101862299380003,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10249347142857144,
"min": 0.10249347142857144,
"max": 0.1984114,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4349086000000002,
"min": 1.3888798,
"max": 2.5700620000000005,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025909779571428566,
"min": 0.00025909779571428566,
"max": 0.00984129886,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036273691399999995,
"min": 0.0036273691399999995,
"max": 0.1170291938,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.02065049484372139,
"min": 0.020578352734446526,
"max": 0.47689738869667053,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.28910693526268005,
"min": 0.28809693455696106,
"max": 3.3382816314697266,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 562.8653846153846,
"min": 548.0555555555555,
"max": 990.53125,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29269.0,
"min": 16721.0,
"max": 32900.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.1678268928080797,
"min": -0.9288875530473888,
"max": 1.1678268928080797,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 60.726998426020145,
"min": -30.62600165605545,
"max": 60.726998426020145,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.1678268928080797,
"min": -0.9288875530473888,
"max": 1.1678268928080797,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 60.726998426020145,
"min": -30.62600165605545,
"max": 60.726998426020145,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.11883449583435252,
"min": 0.11883449583435252,
"max": 9.35483004766352,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 6.179393783386331,
"min": 6.179393783386331,
"max": 159.03211081027985,
"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": "1699545214",
"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/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --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": "1699547300"
},
"total": 2085.752385514,
"count": 1,
"self": 0.475754042999597,
"children": {
"run_training.setup": {
"total": 0.04135089000010339,
"count": 1,
"self": 0.04135089000010339
},
"TrainerController.start_learning": {
"total": 2085.235280581,
"count": 1,
"self": 1.402873584050667,
"children": {
"TrainerController._reset_env": {
"total": 3.3507090670000252,
"count": 1,
"self": 3.3507090670000252
},
"TrainerController.advance": {
"total": 2080.4048105009497,
"count": 63521,
"self": 1.4649461258741212,
"children": {
"env_step": {
"total": 1458.1297558310125,
"count": 63521,
"self": 1324.6028538310604,
"children": {
"SubprocessEnvManager._take_step": {
"total": 132.68692231401292,
"count": 63521,
"self": 4.632193834988357,
"children": {
"TorchPolicy.evaluate": {
"total": 128.05472847902456,
"count": 62568,
"self": 128.05472847902456
}
}
},
"workers": {
"total": 0.8399796859391699,
"count": 63521,
"self": 0.0,
"children": {
"worker_root": {
"total": 2080.7469852739737,
"count": 63521,
"is_parallel": true,
"self": 873.4225161319325,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0020064139998794417,
"count": 1,
"is_parallel": true,
"self": 0.000626497999746789,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013799160001326527,
"count": 8,
"is_parallel": true,
"self": 0.0013799160001326527
}
}
},
"UnityEnvironment.step": {
"total": 0.04738679599995521,
"count": 1,
"is_parallel": true,
"self": 0.000639971000055084,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005541880000237143,
"count": 1,
"is_parallel": true,
"self": 0.0005541880000237143
},
"communicator.exchange": {
"total": 0.04421479199982059,
"count": 1,
"is_parallel": true,
"self": 0.04421479199982059
},
"steps_from_proto": {
"total": 0.0019778450000558223,
"count": 1,
"is_parallel": true,
"self": 0.0004109080005036958,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015669369995521265,
"count": 8,
"is_parallel": true,
"self": 0.0015669369995521265
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1207.3244691420412,
"count": 63520,
"is_parallel": true,
"self": 34.72087793303103,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 25.597091024048723,
"count": 63520,
"is_parallel": true,
"self": 25.597091024048723
},
"communicator.exchange": {
"total": 1045.4388032789814,
"count": 63520,
"is_parallel": true,
"self": 1045.4388032789814
},
"steps_from_proto": {
"total": 101.56769690598003,
"count": 63520,
"is_parallel": true,
"self": 20.771704081065536,
"children": {
"_process_rank_one_or_two_observation": {
"total": 80.79599282491449,
"count": 508160,
"is_parallel": true,
"self": 80.79599282491449
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 620.810108544063,
"count": 63521,
"self": 2.671905848084407,
"children": {
"process_trajectory": {
"total": 122.2644156089741,
"count": 63521,
"self": 122.09406534797427,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17035026099983952,
"count": 2,
"self": 0.17035026099983952
}
}
},
"_update_policy": {
"total": 495.87378708700453,
"count": 453,
"self": 293.68753993699556,
"children": {
"TorchPPOOptimizer.update": {
"total": 202.18624715000897,
"count": 22800,
"self": 202.18624715000897
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1950000953220297e-06,
"count": 1,
"self": 1.1950000953220297e-06
},
"TrainerController._save_models": {
"total": 0.07688623399963035,
"count": 1,
"self": 0.0013492289999703644,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07553700499965998,
"count": 1,
"self": 0.07553700499965998
}
}
}
}
}
}
}