bavolesy's picture
initial commit
0078346
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.3057410717010498,
"min": 0.3057410717010498,
"max": 1.4342204332351685,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 9084.1787109375,
"min": 9084.1787109375,
"max": 43508.51171875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989909.0,
"min": 29952.0,
"max": 989909.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989909.0,
"min": 29952.0,
"max": 989909.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5539206266403198,
"min": -0.10299719125032425,
"max": 0.6862152218818665,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 156.2056121826172,
"min": -24.822322845458984,
"max": 195.03353881835938,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.013841952197253704,
"min": 0.008153458125889301,
"max": 0.40805768966674805,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 3.903430461883545,
"min": 2.2666614055633545,
"max": 98.34190368652344,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07031345083636956,
"min": 0.06391950190438712,
"max": 0.07430830135958136,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0547017625455433,
"min": 0.49047692628723205,
"max": 1.0547017625455433,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.017198719337142798,
"min": 0.0010287105424984936,
"max": 0.017198719337142798,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.257980790057142,
"min": 0.013373237052480415,
"max": 0.257980790057142,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.473537508853333e-06,
"min": 7.473537508853333e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0001121030626328,
"min": 0.0001121030626328,
"max": 0.0036089871970042997,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10249114666666667,
"min": 0.10249114666666667,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5373672,
"min": 1.3886848,
"max": 2.5699389000000004,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.000258865552,
"min": 0.000258865552,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.00388298328,
"min": 0.00388298328,
"max": 0.12030927043000003,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.013263145461678505,
"min": 0.012893399223685265,
"max": 0.6349130868911743,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.19894717633724213,
"min": 0.1805075854063034,
"max": 4.44439172744751,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 337.6276595744681,
"min": 288.5904761904762,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 31737.0,
"min": 15984.0,
"max": 32838.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5559595579162557,
"min": -1.0000000521540642,
"max": 1.7067281359318391,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 146.26019844412804,
"min": -26.38300159573555,
"max": 177.696998603642,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5559595579162557,
"min": -1.0000000521540642,
"max": 1.7067281359318391,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 146.26019844412804,
"min": -26.38300159573555,
"max": 177.696998603642,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.04553986601286909,
"min": 0.04221787511640669,
"max": 13.529486276209354,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.280747405209695,
"min": 4.010698136058636,
"max": 216.47178041934967,
"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": "1695646617",
"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": "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": "1695649138"
},
"total": 2520.263383342,
"count": 1,
"self": 0.5255474509999658,
"children": {
"run_training.setup": {
"total": 0.04276949199993396,
"count": 1,
"self": 0.04276949199993396
},
"TrainerController.start_learning": {
"total": 2519.695066399,
"count": 1,
"self": 1.5344473560662664,
"children": {
"TrainerController._reset_env": {
"total": 4.83715509700005,
"count": 1,
"self": 4.83715509700005
},
"TrainerController.advance": {
"total": 2513.221951739934,
"count": 64252,
"self": 1.5271762350203062,
"children": {
"env_step": {
"total": 1800.1112846859414,
"count": 64252,
"self": 1683.3735125870194,
"children": {
"SubprocessEnvManager._take_step": {
"total": 115.81370257803155,
"count": 64252,
"self": 5.035958570015282,
"children": {
"TorchPolicy.evaluate": {
"total": 110.77774400801627,
"count": 62555,
"self": 110.77774400801627
}
}
},
"workers": {
"total": 0.9240695208904981,
"count": 64252,
"self": 0.0,
"children": {
"worker_root": {
"total": 2514.285859922063,
"count": 64252,
"is_parallel": true,
"self": 954.1701321611172,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0020399559998622863,
"count": 1,
"is_parallel": true,
"self": 0.0006388389997482591,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014011170001140272,
"count": 8,
"is_parallel": true,
"self": 0.0014011170001140272
}
}
},
"UnityEnvironment.step": {
"total": 0.10869806000027893,
"count": 1,
"is_parallel": true,
"self": 0.0005984109998280474,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0011934820004171343,
"count": 1,
"is_parallel": true,
"self": 0.0011934820004171343
},
"communicator.exchange": {
"total": 0.10222122200002559,
"count": 1,
"is_parallel": true,
"self": 0.10222122200002559
},
"steps_from_proto": {
"total": 0.004684945000008156,
"count": 1,
"is_parallel": true,
"self": 0.00041927399979613256,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0042656710002120235,
"count": 8,
"is_parallel": true,
"self": 0.0042656710002120235
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1560.115727760946,
"count": 64251,
"is_parallel": true,
"self": 36.713801330975,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.370599064029193,
"count": 64251,
"is_parallel": true,
"self": 24.370599064029193
},
"communicator.exchange": {
"total": 1384.0811511739835,
"count": 64251,
"is_parallel": true,
"self": 1384.0811511739835
},
"steps_from_proto": {
"total": 114.95017619195823,
"count": 64251,
"is_parallel": true,
"self": 22.680684548193312,
"children": {
"_process_rank_one_or_two_observation": {
"total": 92.26949164376492,
"count": 514008,
"is_parallel": true,
"self": 92.26949164376492
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 711.5834908189722,
"count": 64252,
"self": 2.9083015990704553,
"children": {
"process_trajectory": {
"total": 120.39514042290557,
"count": 64252,
"self": 120.17886073990621,
"children": {
"RLTrainer._checkpoint": {
"total": 0.21627968299935674,
"count": 2,
"self": 0.21627968299935674
}
}
},
"_update_policy": {
"total": 588.2800487969962,
"count": 457,
"self": 384.80291549802587,
"children": {
"TorchPPOOptimizer.update": {
"total": 203.47713329897033,
"count": 22812,
"self": 203.47713329897033
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.157000042439904e-06,
"count": 1,
"self": 1.157000042439904e-06
},
"TrainerController._save_models": {
"total": 0.10151104899978236,
"count": 1,
"self": 0.001518237999334815,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09999281100044755,
"count": 1,
"self": 0.09999281100044755
}
}
}
}
}
}
}