Ktang2k's picture
default config
ec86cfa
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.3970147371292114,
"min": 0.3970147371292114,
"max": 1.3640958070755005,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 11967.6123046875,
"min": 11967.6123046875,
"max": 41381.2109375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989979.0,
"min": 29952.0,
"max": 989979.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989979.0,
"min": 29952.0,
"max": 989979.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.6159937977790833,
"min": -0.0849965512752533,
"max": 0.6527718901634216,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 176.79022216796875,
"min": -20.399171829223633,
"max": 184.7344512939453,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.025621892884373665,
"min": -0.002717418596148491,
"max": 0.3476933240890503,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 7.353483200073242,
"min": -0.6793546676635742,
"max": 83.7940902709961,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07052308173193264,
"min": 0.06476805409294598,
"max": 0.07669804216253959,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9873231442470569,
"min": 0.5368862951377771,
"max": 1.0757560585037687,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01346772093425638,
"min": 0.0004181058016686821,
"max": 0.015075010417443562,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.1885480930795893,
"min": 0.0058534812233615495,
"max": 0.21105014584420986,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.355540405328573e-06,
"min": 7.355540405328573e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010297756567460002,
"min": 0.00010297756567460002,
"max": 0.0036338143887285996,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10245181428571427,
"min": 0.10245181428571427,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4343253999999999,
"min": 1.3886848,
"max": 2.6112714000000006,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002549362471428572,
"min": 0.0002549362471428572,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0035691074600000014,
"min": 0.0035691074600000014,
"max": 0.12114601286,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.01338155660778284,
"min": 0.01275926548987627,
"max": 0.46160200238227844,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.18734179437160492,
"min": 0.17862971127033234,
"max": 3.2312140464782715,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 319.3263157894737,
"min": 313.0105263157895,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30336.0,
"min": 15984.0,
"max": 32636.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.659610508696029,
"min": -1.0000000521540642,
"max": 1.659610508696029,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 157.66299832612276,
"min": -30.995201617479324,
"max": 157.66299832612276,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.659610508696029,
"min": -1.0000000521540642,
"max": 1.659610508696029,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 157.66299832612276,
"min": -30.995201617479324,
"max": 157.66299832612276,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.04463494264652438,
"min": 0.0410864054966767,
"max": 8.935822810977697,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.240319551419816,
"min": 3.9032085221842863,
"max": 142.97316497564316,
"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": "1684120331",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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=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": "1684122595"
},
"total": 2263.729596354,
"count": 1,
"self": 0.5251459940000132,
"children": {
"run_training.setup": {
"total": 0.036591670999996495,
"count": 1,
"self": 0.036591670999996495
},
"TrainerController.start_learning": {
"total": 2263.1678586890002,
"count": 1,
"self": 1.4347082808990308,
"children": {
"TrainerController._reset_env": {
"total": 3.7416690970001127,
"count": 1,
"self": 3.7416690970001127
},
"TrainerController.advance": {
"total": 2257.901242342101,
"count": 63973,
"self": 1.5171635899873763,
"children": {
"env_step": {
"total": 1614.3949481980367,
"count": 63973,
"self": 1499.7957931988408,
"children": {
"SubprocessEnvManager._take_step": {
"total": 113.75632965702744,
"count": 63973,
"self": 5.023087122990546,
"children": {
"TorchPolicy.evaluate": {
"total": 108.73324253403689,
"count": 62582,
"self": 108.73324253403689
}
}
},
"workers": {
"total": 0.8428253421684531,
"count": 63973,
"self": 0.0,
"children": {
"worker_root": {
"total": 2257.839790867032,
"count": 63973,
"is_parallel": true,
"self": 876.9798437640175,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0018147999999200692,
"count": 1,
"is_parallel": true,
"self": 0.0005963609994523722,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001218439000467697,
"count": 8,
"is_parallel": true,
"self": 0.001218439000467697
}
}
},
"UnityEnvironment.step": {
"total": 0.047625121000237414,
"count": 1,
"is_parallel": true,
"self": 0.0005261550004433957,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005442589999802294,
"count": 1,
"is_parallel": true,
"self": 0.0005442589999802294
},
"communicator.exchange": {
"total": 0.04449686199995995,
"count": 1,
"is_parallel": true,
"self": 0.04449686199995995
},
"steps_from_proto": {
"total": 0.0020578449998538417,
"count": 1,
"is_parallel": true,
"self": 0.00045985099950485164,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00159799400034899,
"count": 8,
"is_parallel": true,
"self": 0.00159799400034899
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1380.8599471030147,
"count": 63972,
"is_parallel": true,
"self": 32.26467700317335,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.172425137941445,
"count": 63972,
"is_parallel": true,
"self": 24.172425137941445
},
"communicator.exchange": {
"total": 1219.047177722971,
"count": 63972,
"is_parallel": true,
"self": 1219.047177722971
},
"steps_from_proto": {
"total": 105.37566723892905,
"count": 63972,
"is_parallel": true,
"self": 21.886387867012218,
"children": {
"_process_rank_one_or_two_observation": {
"total": 83.48927937191684,
"count": 511776,
"is_parallel": true,
"self": 83.48927937191684
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 641.9891305540768,
"count": 63973,
"self": 2.6894545680315787,
"children": {
"process_trajectory": {
"total": 114.4197851780441,
"count": 63973,
"self": 114.08209785104373,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3376873270003671,
"count": 2,
"self": 0.3376873270003671
}
}
},
"_update_policy": {
"total": 524.8798908080012,
"count": 455,
"self": 338.9867737860159,
"children": {
"TorchPPOOptimizer.update": {
"total": 185.8931170219853,
"count": 22797,
"self": 185.8931170219853
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.589994078851305e-07,
"count": 1,
"self": 9.589994078851305e-07
},
"TrainerController._save_models": {
"total": 0.09023801000057574,
"count": 1,
"self": 0.0013988110003992915,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08883919900017645,
"count": 1,
"self": 0.08883919900017645
}
}
}
}
}
}
}