ppo-Pyramids / run_logs /timers.json
brand25's picture
First Push
5f6378c
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.21311897039413452,
"min": 0.20187313854694366,
"max": 1.5083198547363281,
"count": 100
},
"Pyramids.Policy.Entropy.sum": {
"value": 6376.51953125,
"min": 6020.66455078125,
"max": 45756.390625,
"count": 100
},
"Pyramids.Step.mean": {
"value": 2999991.0,
"min": 29952.0,
"max": 2999991.0,
"count": 100
},
"Pyramids.Step.sum": {
"value": 2999991.0,
"min": 29952.0,
"max": 2999991.0,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.7066445350646973,
"min": -0.10475429147481918,
"max": 0.8011800646781921,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 204.92691040039062,
"min": -25.245784759521484,
"max": 234.74575805664062,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 5.7399967772653326e-05,
"min": -0.008259429596364498,
"max": 0.3433760702610016,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 0.016645990312099457,
"min": -2.4117534160614014,
"max": 81.380126953125,
"count": 100
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06795262274820181,
"min": 0.06581571141127608,
"max": 0.0743658824946212,
"count": 100
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9513367184748253,
"min": 0.5107877309343459,
"max": 1.0895459632544469,
"count": 100
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015430883205830345,
"min": 6.843201560795201e-05,
"max": 0.016125410928257877,
"count": 100
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.21603236488162483,
"min": 0.000821184187295424,
"max": 0.22880325691464046,
"count": 100
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.4773995075666661e-06,
"min": 1.4773995075666661e-06,
"max": 0.00029838354339596195,
"count": 100
},
"Pyramids.Policy.LearningRate.sum": {
"value": 2.0683593105933326e-05,
"min": 2.0683593105933326e-05,
"max": 0.0036750727749758003,
"count": 100
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10049243333333333,
"min": 0.10049243333333333,
"max": 0.19946118095238097,
"count": 100
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4068940666666665,
"min": 1.3962282666666668,
"max": 2.6775450333333337,
"count": 100
},
"Pyramids.Policy.Beta.mean": {
"value": 5.9194089999999996e-05,
"min": 5.9194089999999996e-05,
"max": 0.009946171977142856,
"count": 100
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0008287172599999999,
"min": 0.0008287172599999999,
"max": 0.12251991758000001,
"count": 100
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.004000221379101276,
"min": 0.003829118562862277,
"max": 0.34600672125816345,
"count": 100
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.05600310117006302,
"min": 0.053755585104227066,
"max": 2.4220471382141113,
"count": 100
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 249.172131147541,
"min": 226.01652892561984,
"max": 999.0,
"count": 100
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30399.0,
"min": 15984.0,
"max": 34319.0,
"count": 100
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7344294978214092,
"min": -1.0000000521540642,
"max": 1.7573655583575123,
"count": 100
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 211.60039873421192,
"min": -31.997601687908173,
"max": 214.3985981196165,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7344294978214092,
"min": -1.0000000521540642,
"max": 1.7573655583575123,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 211.60039873421192,
"min": -31.997601687908173,
"max": 214.3985981196165,
"count": 100
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.010308968158869157,
"min": 0.009410948323450418,
"max": 7.215126221999526,
"count": 100
},
"Pyramids.Policy.RndReward.sum": {
"value": 1.2576941153820371,
"min": 1.148135695460951,
"max": 115.44201955199242,
"count": 100
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1679034561",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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=Pyramids1 --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": "1679041131"
},
"total": 6570.087166446,
"count": 1,
"self": 0.5473769240006732,
"children": {
"run_training.setup": {
"total": 0.10370258299997204,
"count": 1,
"self": 0.10370258299997204
},
"TrainerController.start_learning": {
"total": 6569.436086938999,
"count": 1,
"self": 3.8439056999350214,
"children": {
"TrainerController._reset_env": {
"total": 11.667421850999972,
"count": 1,
"self": 11.667421850999972
},
"TrainerController.advance": {
"total": 6553.833691873065,
"count": 193398,
"self": 4.277091273014776,
"children": {
"env_step": {
"total": 4714.97888251102,
"count": 193398,
"self": 4402.010080359833,
"children": {
"SubprocessEnvManager._take_step": {
"total": 310.570566592992,
"count": 193398,
"self": 14.017777244057982,
"children": {
"TorchPolicy.evaluate": {
"total": 296.552789348934,
"count": 187556,
"self": 296.552789348934
}
}
},
"workers": {
"total": 2.3982355581945853,
"count": 193398,
"self": 0.0,
"children": {
"worker_root": {
"total": 6556.312545580925,
"count": 193398,
"is_parallel": true,
"self": 2486.860388669865,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0056179680000241206,
"count": 1,
"is_parallel": true,
"self": 0.004148383000085687,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014695849999384336,
"count": 8,
"is_parallel": true,
"self": 0.0014695849999384336
}
}
},
"UnityEnvironment.step": {
"total": 0.05066991199998938,
"count": 1,
"is_parallel": true,
"self": 0.0006059489999756806,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00047731099999737125,
"count": 1,
"is_parallel": true,
"self": 0.00047731099999737125
},
"communicator.exchange": {
"total": 0.047742249999998876,
"count": 1,
"is_parallel": true,
"self": 0.047742249999998876
},
"steps_from_proto": {
"total": 0.0018444020000174532,
"count": 1,
"is_parallel": true,
"self": 0.00042501400002947776,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014193879999879755,
"count": 8,
"is_parallel": true,
"self": 0.0014193879999879755
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 4069.45215691106,
"count": 193397,
"is_parallel": true,
"self": 95.87534728598621,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 68.12388870189858,
"count": 193397,
"is_parallel": true,
"self": 68.12388870189858
},
"communicator.exchange": {
"total": 3630.1031114250377,
"count": 193397,
"is_parallel": true,
"self": 3630.1031114250377
},
"steps_from_proto": {
"total": 275.34980949813746,
"count": 193397,
"is_parallel": true,
"self": 58.18446761838919,
"children": {
"_process_rank_one_or_two_observation": {
"total": 217.16534187974827,
"count": 1547176,
"is_parallel": true,
"self": 217.16534187974827
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1834.5777180890304,
"count": 193398,
"self": 7.543297309118088,
"children": {
"process_trajectory": {
"total": 346.20808438892254,
"count": 193398,
"self": 345.4832726679231,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7248117209994689,
"count": 6,
"self": 0.7248117209994689
}
}
},
"_update_policy": {
"total": 1480.8263363909898,
"count": 1383,
"self": 942.258057564874,
"children": {
"TorchPPOOptimizer.update": {
"total": 538.5682788261158,
"count": 68469,
"self": 538.5682788261158
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.010000212583691e-07,
"count": 1,
"self": 9.010000212583691e-07
},
"TrainerController._save_models": {
"total": 0.0910666139998284,
"count": 1,
"self": 0.0014608860001317225,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08960572799969668,
"count": 1,
"self": 0.08960572799969668
}
}
}
}
}
}
}