felixquinihildebet's picture
version 1
2767f74
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.18401144444942474,
"min": 0.18192239105701447,
"max": 1.5117591619491577,
"count": 100
},
"Pyramids.Policy.Entropy.sum": {
"value": 5496.7900390625,
"min": 5384.90283203125,
"max": 45860.7265625,
"count": 100
},
"Pyramids.Step.mean": {
"value": 2999923.0,
"min": 29952.0,
"max": 2999923.0,
"count": 100
},
"Pyramids.Step.sum": {
"value": 2999923.0,
"min": 29952.0,
"max": 2999923.0,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.7807646989822388,
"min": -0.14062584936618805,
"max": 0.7975755333900452,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 225.6409912109375,
"min": -33.32832717895508,
"max": 237.67750549316406,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.00847997609525919,
"min": -0.015897652134299278,
"max": 0.2882915735244751,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 2.4507131576538086,
"min": -4.419547080993652,
"max": 68.32510375976562,
"count": 100
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06916296936935437,
"min": 0.062430350018995516,
"max": 0.0760407712572161,
"count": 100
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9682815711709611,
"min": 0.4734619167484825,
"max": 1.0744486110682676,
"count": 100
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01426633478815541,
"min": 9.384191115708912e-05,
"max": 0.018998097348628087,
"count": 100
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.19972868703417573,
"min": 0.0012199448450421586,
"max": 0.2659733628807932,
"count": 100
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.4535066583880929e-06,
"min": 1.4535066583880929e-06,
"max": 0.00029838354339596195,
"count": 100
},
"Pyramids.Policy.LearningRate.sum": {
"value": 2.03490932174333e-05,
"min": 2.03490932174333e-05,
"max": 0.0038011308329564336,
"count": 100
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10048446904761905,
"min": 0.10048446904761905,
"max": 0.19946118095238097,
"count": 100
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4067825666666667,
"min": 1.3897045333333333,
"max": 2.6774514666666667,
"count": 100
},
"Pyramids.Policy.Beta.mean": {
"value": 5.839845785714278e-05,
"min": 5.839845785714278e-05,
"max": 0.009946171977142856,
"count": 100
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0008175784099999989,
"min": 0.0008175784099999989,
"max": 0.12671765230999998,
"count": 100
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.0035090025048702955,
"min": 0.0033602232579141855,
"max": 0.3583499789237976,
"count": 100
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.049126036465168,
"min": 0.047043126076459885,
"max": 2.5084497928619385,
"count": 100
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 226.9763779527559,
"min": 226.9763779527559,
"max": 999.0,
"count": 100
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28826.0,
"min": 15984.0,
"max": 32419.0,
"count": 100
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.772992174490355,
"min": -1.0000000521540642,
"max": 1.772992174490355,
"count": 100
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 226.94299833476543,
"min": -32.000001668930054,
"max": 232.62259803712368,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.772992174490355,
"min": -1.0000000521540642,
"max": 1.772992174490355,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 226.94299833476543,
"min": -32.000001668930054,
"max": 232.62259803712368,
"count": 100
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.008412265540130193,
"min": 0.008412265540130193,
"max": 8.161293068900704,
"count": 100
},
"Pyramids.Policy.RndReward.sum": {
"value": 1.0767699891366647,
"min": 1.0212563066816074,
"max": 130.58068910241127,
"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": "1695590386",
"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": "1695598149"
},
"total": 7762.645495506001,
"count": 1,
"self": 0.4373200910004016,
"children": {
"run_training.setup": {
"total": 0.03906203899987304,
"count": 1,
"self": 0.03906203899987304
},
"TrainerController.start_learning": {
"total": 7762.1691133760005,
"count": 1,
"self": 5.420031661064058,
"children": {
"TrainerController._reset_env": {
"total": 0.9867166960002578,
"count": 1,
"self": 0.9867166960002578
},
"TrainerController.advance": {
"total": 7755.694253171936,
"count": 193567,
"self": 4.797179200135361,
"children": {
"env_step": {
"total": 4443.837383705893,
"count": 193567,
"self": 4095.3482261186055,
"children": {
"SubprocessEnvManager._take_step": {
"total": 345.25605381622245,
"count": 193567,
"self": 12.357338313852779,
"children": {
"TorchPolicy.evaluate": {
"total": 332.89871550236967,
"count": 187552,
"self": 332.89871550236967
}
}
},
"workers": {
"total": 3.2331037710655437,
"count": 193567,
"self": 0.0,
"children": {
"worker_root": {
"total": 7749.4370880370425,
"count": 193567,
"is_parallel": true,
"self": 3993.864594613538,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001922189999731927,
"count": 1,
"is_parallel": true,
"self": 0.0006558399991263286,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012663500006055983,
"count": 8,
"is_parallel": true,
"self": 0.0012663500006055983
}
}
},
"UnityEnvironment.step": {
"total": 0.05020596799977284,
"count": 1,
"is_parallel": true,
"self": 0.005476868999267026,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003017000003637804,
"count": 1,
"is_parallel": true,
"self": 0.0003017000003637804
},
"communicator.exchange": {
"total": 0.041986079000253085,
"count": 1,
"is_parallel": true,
"self": 0.041986079000253085
},
"steps_from_proto": {
"total": 0.0024413199998889468,
"count": 1,
"is_parallel": true,
"self": 0.0003079200000684068,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00213339999982054,
"count": 8,
"is_parallel": true,
"self": 0.00213339999982054
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 3755.5724934235045,
"count": 193566,
"is_parallel": true,
"self": 92.20642083445955,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 48.38629353219858,
"count": 193566,
"is_parallel": true,
"self": 48.38629353219858
},
"communicator.exchange": {
"total": 3334.081736549825,
"count": 193566,
"is_parallel": true,
"self": 3334.081736549825
},
"steps_from_proto": {
"total": 280.8980425070213,
"count": 193566,
"is_parallel": true,
"self": 58.370668730314264,
"children": {
"_process_rank_one_or_two_observation": {
"total": 222.527373776707,
"count": 1548528,
"is_parallel": true,
"self": 222.527373776707
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 3307.059690265907,
"count": 193567,
"self": 9.925616036094652,
"children": {
"process_trajectory": {
"total": 362.11183932382437,
"count": 193567,
"self": 361.6086341048226,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5032052190017566,
"count": 6,
"self": 0.5032052190017566
}
}
},
"_update_policy": {
"total": 2935.022234905988,
"count": 1388,
"self": 879.7769360649281,
"children": {
"TorchPPOOptimizer.update": {
"total": 2055.24529884106,
"count": 68406,
"self": 2055.24529884106
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.799997885944322e-07,
"count": 1,
"self": 8.799997885944322e-07
},
"TrainerController._save_models": {
"total": 0.06811096700039343,
"count": 1,
"self": 0.0012169199999334523,
"children": {
"RLTrainer._checkpoint": {
"total": 0.06689404700045998,
"count": 1,
"self": 0.06689404700045998
}
}
}
}
}
}
}