QuickSilver007's picture
Trained Pyramids agent upload
255f58e
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5025023818016052,
"min": 0.4954706132411957,
"max": 1.4921729564666748,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 15067.03125,
"min": 15014.7412109375,
"max": 45266.55859375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989957.0,
"min": 29952.0,
"max": 989957.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989957.0,
"min": 29952.0,
"max": 989957.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.43156328797340393,
"min": -0.11121068894863129,
"max": 0.5647807717323303,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 114.79583740234375,
"min": -26.35693359375,
"max": 156.44427490234375,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.027206676080822945,
"min": -0.2914373576641083,
"max": 0.37699419260025024,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -7.23697566986084,
"min": -78.97952270507812,
"max": 89.34762573242188,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06745950118610858,
"min": 0.06591277108689873,
"max": 0.0718440967154845,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.94443301660552,
"min": 0.4886386653467954,
"max": 1.0732553767607613,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.016013090989526104,
"min": 0.00030833215952521045,
"max": 0.023195202232418218,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.22418327385336548,
"min": 0.004008318073827736,
"max": 0.32473283125385505,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.710247429950002e-06,
"min": 7.710247429950002e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010794346401930003,
"min": 0.00010794346401930003,
"max": 0.0033820256726582003,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10257005,
"min": 0.10257005,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4359807,
"min": 1.3886848,
"max": 2.5273418000000003,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002667479950000001,
"min": 0.0002667479950000001,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003734471930000001,
"min": 0.003734471930000001,
"max": 0.11276144581999999,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.00880816113203764,
"min": 0.008608461357653141,
"max": 0.37863412499427795,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1233142539858818,
"min": 0.12051846086978912,
"max": 2.6504387855529785,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 427.8378378378378,
"min": 374.32,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 31660.0,
"min": 15984.0,
"max": 33911.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.436016415079979,
"min": -1.0000000521540642,
"max": 1.577045217777292,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 104.82919830083847,
"min": -31.996001660823822,
"max": 132.47179829329252,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.436016415079979,
"min": -1.0000000521540642,
"max": 1.577045217777292,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 104.82919830083847,
"min": -31.996001660823822,
"max": 132.47179829329252,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.0390342784605359,
"min": 0.0335061490811876,
"max": 7.762439802289009,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.8495023276191205,
"min": 2.618655948404921,
"max": 124.19903683662415,
"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": "1656146094",
"python_version": "3.7.13 (default, Apr 24 2022, 01:04:09) \n[GCC 7.5.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/PyramidsRND.yaml --env=/content/ml-agents/trained-envs-executables/linux/Pyramids/Pyramids --run-id=First Training --force --no-graphics",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1656149187"
},
"total": 3093.621723573,
"count": 1,
"self": 0.5792813749994821,
"children": {
"run_training.setup": {
"total": 0.06636839900011182,
"count": 1,
"self": 0.06636839900011182
},
"TrainerController.start_learning": {
"total": 3092.9760737990005,
"count": 1,
"self": 2.4741103200740326,
"children": {
"TrainerController._reset_env": {
"total": 8.725167850000162,
"count": 1,
"self": 8.725167850000162
},
"TrainerController.advance": {
"total": 3081.6708474279267,
"count": 63671,
"self": 2.552840573861886,
"children": {
"env_step": {
"total": 1832.180661930931,
"count": 63671,
"self": 1681.7573832998764,
"children": {
"SubprocessEnvManager._take_step": {
"total": 148.88740735094643,
"count": 63671,
"self": 7.053575330899093,
"children": {
"TorchPolicy.evaluate": {
"total": 141.83383202004734,
"count": 62563,
"self": 31.184050374058643,
"children": {
"TorchPolicy.sample_actions": {
"total": 110.6497816459887,
"count": 62563,
"self": 110.6497816459887
}
}
}
}
},
"workers": {
"total": 1.53587128010804,
"count": 63671,
"self": 0.0,
"children": {
"worker_root": {
"total": 3086.7966180901794,
"count": 63671,
"is_parallel": true,
"self": 1576.42598972627,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007325150000269787,
"count": 1,
"is_parallel": true,
"self": 0.005629217000659992,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001695932999609795,
"count": 8,
"is_parallel": true,
"self": 0.001695932999609795
}
}
},
"UnityEnvironment.step": {
"total": 0.07035671099993124,
"count": 1,
"is_parallel": true,
"self": 0.000710478999735642,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0006465070000558626,
"count": 1,
"is_parallel": true,
"self": 0.0006465070000558626
},
"communicator.exchange": {
"total": 0.06669388599993908,
"count": 1,
"is_parallel": true,
"self": 0.06669388599993908
},
"steps_from_proto": {
"total": 0.002305839000200649,
"count": 1,
"is_parallel": true,
"self": 0.0006614260000787908,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016444130001218582,
"count": 8,
"is_parallel": true,
"self": 0.0016444130001218582
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1510.3706283639094,
"count": 63670,
"is_parallel": true,
"self": 40.86527133974096,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 26.713646200000767,
"count": 63670,
"is_parallel": true,
"self": 26.713646200000767
},
"communicator.exchange": {
"total": 1296.5562163450732,
"count": 63670,
"is_parallel": true,
"self": 1296.5562163450732
},
"steps_from_proto": {
"total": 146.23549447909454,
"count": 63670,
"is_parallel": true,
"self": 40.840835090034034,
"children": {
"_process_rank_one_or_two_observation": {
"total": 105.39465938906051,
"count": 509360,
"is_parallel": true,
"self": 105.39465938906051
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1246.9373449231339,
"count": 63671,
"self": 4.858867588176508,
"children": {
"process_trajectory": {
"total": 224.24579585895845,
"count": 63671,
"self": 224.01144094195843,
"children": {
"RLTrainer._checkpoint": {
"total": 0.23435491700001876,
"count": 2,
"self": 0.23435491700001876
}
}
},
"_update_policy": {
"total": 1017.8326814759989,
"count": 446,
"self": 280.58072937801626,
"children": {
"TorchPPOOptimizer.update": {
"total": 737.2519520979827,
"count": 22812,
"self": 737.2519520979827
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4399993233382702e-06,
"count": 1,
"self": 1.4399993233382702e-06
},
"TrainerController._save_models": {
"total": 0.10594676100026845,
"count": 1,
"self": 0.0021927860007053823,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10375397499956307,
"count": 1,
"self": 0.10375397499956307
}
}
}
}
}
}
}