Alexander Chernyavskiy
Trained Pyramids agent
fb7365e
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5217984914779663,
"min": 0.5217984914779663,
"max": 1.3929883241653442,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 15478.630859375,
"min": 15478.630859375,
"max": 42257.6953125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989951.0,
"min": 29952.0,
"max": 989951.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989951.0,
"min": 29952.0,
"max": 989951.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.3243556022644043,
"min": -0.09963350743055344,
"max": 0.38994845747947693,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 84.98117065429688,
"min": -24.111309051513672,
"max": 103.72628784179688,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 5.876914024353027,
"min": -0.23564189672470093,
"max": 5.9755659103393555,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 1539.75146484375,
"min": -61.26689147949219,
"max": 1607.42724609375,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06546258268799927,
"min": 0.06444343320279595,
"max": 0.07492467084329081,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9164761576319898,
"min": 0.5244726959030357,
"max": 1.0482152824891575,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 3.497891251159524,
"min": 0.0001863230602106107,
"max": 4.027044673893778,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 48.97047751623334,
"min": 0.002422199782737939,
"max": 56.3786254345129,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.755911700442857e-06,
"min": 7.755911700442857e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0001085827638062,
"min": 0.0001085827638062,
"max": 0.003507080330973299,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10258527142857142,
"min": 0.10258527142857142,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4361937999999999,
"min": 1.3886848,
"max": 2.5690267,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026826861571428576,
"min": 0.00026826861571428576,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0037557606200000005,
"min": 0.0037557606200000005,
"max": 0.11692576732999999,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.00835955236107111,
"min": 0.00835955236107111,
"max": 0.49735310673713684,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.11703372746706009,
"min": 0.11703372746706009,
"max": 3.4814717769622803,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 499.78333333333336,
"min": 430.3857142857143,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29987.0,
"min": 15984.0,
"max": 33016.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.1334366284310817,
"min": -1.0000000521540642,
"max": 1.4329558625159895,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 68.0061977058649,
"min": -31.99640166759491,
"max": 99.86939814686775,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.1334366284310817,
"min": -1.0000000521540642,
"max": 1.4329558625159895,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 68.0061977058649,
"min": -31.99640166759491,
"max": 99.86939814686775,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.044238226128557774,
"min": 0.0390701954407525,
"max": 10.392275916412473,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.6542935677134665,
"min": 2.6542935677134665,
"max": 166.27641466259956,
"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": "1656054580",
"python_version": "3.9.7 (tags/v3.9.7:1016ef3, Aug 30 2021, 20:19:38) [MSC v.1929 64 bit (AMD64)]",
"command_line_arguments": "C:\\Users\\Alexander\\AppData\\Local\\Programs\\Python\\Python39\\Scripts\\mlagents-learn --force config\\ppo\\PyramidsRND.yaml --env=trained-envs-executables\\windows\\Pyramids --no-graphics --run-id=The run",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.10.2+cpu",
"numpy_version": "1.21.2",
"end_time_seconds": "1656057978"
},
"total": 3398.14364,
"count": 1,
"self": 4.84618829999954,
"children": {
"run_training.setup": {
"total": 0.20310749999999977,
"count": 1,
"self": 0.20310749999999977
},
"TrainerController.start_learning": {
"total": 3393.0943442000003,
"count": 1,
"self": 2.6902043000154663,
"children": {
"TrainerController._reset_env": {
"total": 3.5748520999999998,
"count": 1,
"self": 3.5748520999999998
},
"TrainerController.advance": {
"total": 3386.4623875999846,
"count": 63483,
"self": 2.702206699967519,
"children": {
"env_step": {
"total": 1720.0373506999936,
"count": 63483,
"self": 1557.9982408000124,
"children": {
"SubprocessEnvManager._take_step": {
"total": 160.42501390000155,
"count": 63483,
"self": 7.455559199983156,
"children": {
"TorchPolicy.evaluate": {
"total": 152.9694547000184,
"count": 62551,
"self": 33.34210999997191,
"children": {
"TorchPolicy.sample_actions": {
"total": 119.62734470004648,
"count": 62551,
"self": 119.62734470004648
}
}
}
}
},
"workers": {
"total": 1.6140959999795896,
"count": 63483,
"self": 0.0,
"children": {
"worker_root": {
"total": 3385.259170400034,
"count": 63483,
"is_parallel": true,
"self": 2011.913537600056,
"children": {
"steps_from_proto": {
"total": 0.001860600000000101,
"count": 1,
"is_parallel": true,
"self": 0.0004859000000001501,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001374699999999951,
"count": 8,
"is_parallel": true,
"self": 0.001374699999999951
}
}
},
"UnityEnvironment.step": {
"total": 1373.3437721999776,
"count": 63483,
"is_parallel": true,
"self": 43.198415599947566,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 31.394529399984755,
"count": 63483,
"is_parallel": true,
"self": 31.394529399984755
},
"communicator.exchange": {
"total": 1170.637535500011,
"count": 63483,
"is_parallel": true,
"self": 1170.637535500011
},
"steps_from_proto": {
"total": 128.11329170003435,
"count": 63483,
"is_parallel": true,
"self": 31.663106400046075,
"children": {
"_process_rank_one_or_two_observation": {
"total": 96.45018529998828,
"count": 507864,
"is_parallel": true,
"self": 96.45018529998828
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1663.7228302000233,
"count": 63483,
"self": 4.467717300024333,
"children": {
"process_trajectory": {
"total": 301.0592478999946,
"count": 63483,
"self": 300.59151829999485,
"children": {
"RLTrainer._checkpoint": {
"total": 0.46772959999975683,
"count": 2,
"self": 0.46772959999975683
}
}
},
"_update_policy": {
"total": 1358.1958650000045,
"count": 446,
"self": 393.2782437999815,
"children": {
"TorchPPOOptimizer.update": {
"total": 964.917621200023,
"count": 22803,
"self": 964.917621200023
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2000000424450263e-06,
"count": 1,
"self": 1.2000000424450263e-06
},
"TrainerController._save_models": {
"total": 0.3668990000001031,
"count": 1,
"self": 0.05187500000010914,
"children": {
"RLTrainer._checkpoint": {
"total": 0.315023999999994,
"count": 1,
"self": 0.315023999999994
}
}
}
}
}
}
}