granenko's picture
first push
b31604d verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.3722181022167206,
"min": 0.3652188181877136,
"max": 1.4612599611282349,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 11041.4775390625,
"min": 10956.564453125,
"max": 44328.78125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989889.0,
"min": 29952.0,
"max": 989889.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989889.0,
"min": 29952.0,
"max": 989889.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.6727520227432251,
"min": -0.0814158096909523,
"max": 0.6785497069358826,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 189.716064453125,
"min": -19.702625274658203,
"max": 192.70811462402344,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.004181215073913336,
"min": -0.04229750484228134,
"max": 0.28032979369163513,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 1.1791026592254639,
"min": -11.504920959472656,
"max": 67.2791519165039,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06819206931543828,
"min": 0.06517402082722418,
"max": 0.0736315022207616,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9546889704161359,
"min": 0.4682105205546337,
"max": 1.0616145152210565,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.014282160060899595,
"min": 0.0008892854913285237,
"max": 0.016477229700022793,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.19995024085259433,
"min": 0.011560711387270809,
"max": 0.24715844550034188,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.6031903227785695e-06,
"min": 7.6031903227785695e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010644466451889998,
"min": 0.00010644466451889998,
"max": 0.0033784091738637,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10253436428571429,
"min": 0.10253436428571429,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4354811,
"min": 1.3691136000000002,
"max": 2.5261363,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026318299214285717,
"min": 0.00026318299214285717,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.00368456189,
"min": 0.00368456189,
"max": 0.11264101637000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.01050561387091875,
"min": 0.01050561387091875,
"max": 0.4022192358970642,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.14707858860492706,
"min": 0.14707858860492706,
"max": 2.8155345916748047,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 294.0857142857143,
"min": 275.5686274509804,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30879.0,
"min": 15984.0,
"max": 32896.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6487561716919854,
"min": -1.0000000521540642,
"max": 1.7066666445895737,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 173.11939802765846,
"min": -32.000001668930054,
"max": 174.07999774813652,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6487561716919854,
"min": -1.0000000521540642,
"max": 1.7066666445895737,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 173.11939802765846,
"min": -32.000001668930054,
"max": 174.07999774813652,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.03162413857069277,
"min": 0.03162413857069277,
"max": 7.427429661154747,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.3205345499227406,
"min": 3.2736870716908015,
"max": 118.83887457847595,
"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": "1757958339",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1757960484"
},
"total": 2144.953781472,
"count": 1,
"self": 0.47990721399992253,
"children": {
"run_training.setup": {
"total": 0.02177242700008719,
"count": 1,
"self": 0.02177242700008719
},
"TrainerController.start_learning": {
"total": 2144.452101831,
"count": 1,
"self": 1.2502720610182223,
"children": {
"TrainerController._reset_env": {
"total": 2.1227547319999758,
"count": 1,
"self": 2.1227547319999758
},
"TrainerController.advance": {
"total": 2140.9973229299812,
"count": 64008,
"self": 1.3442744470139587,
"children": {
"env_step": {
"total": 1484.0234126739188,
"count": 64008,
"self": 1342.9326023759563,
"children": {
"SubprocessEnvManager._take_step": {
"total": 140.32839579296342,
"count": 64008,
"self": 4.443138182007715,
"children": {
"TorchPolicy.evaluate": {
"total": 135.8852576109557,
"count": 62558,
"self": 135.8852576109557
}
}
},
"workers": {
"total": 0.7624145049990148,
"count": 64008,
"self": 0.0,
"children": {
"worker_root": {
"total": 2140.0988803149853,
"count": 64008,
"is_parallel": true,
"self": 903.0980961138962,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0019210570003451721,
"count": 1,
"is_parallel": true,
"self": 0.0006099040006120049,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013111529997331672,
"count": 8,
"is_parallel": true,
"self": 0.0013111529997331672
}
}
},
"UnityEnvironment.step": {
"total": 0.0466740970000501,
"count": 1,
"is_parallel": true,
"self": 0.0005381390001275577,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00044681700001092395,
"count": 1,
"is_parallel": true,
"self": 0.00044681700001092395
},
"communicator.exchange": {
"total": 0.04404755699988527,
"count": 1,
"is_parallel": true,
"self": 0.04404755699988527
},
"steps_from_proto": {
"total": 0.0016415840000263415,
"count": 1,
"is_parallel": true,
"self": 0.00034887000037997495,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012927139996463666,
"count": 8,
"is_parallel": true,
"self": 0.0012927139996463666
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1237.0007842010891,
"count": 64007,
"is_parallel": true,
"self": 30.989987952219508,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 21.921354103873,
"count": 64007,
"is_parallel": true,
"self": 21.921354103873
},
"communicator.exchange": {
"total": 1092.5553492050035,
"count": 64007,
"is_parallel": true,
"self": 1092.5553492050035
},
"steps_from_proto": {
"total": 91.53409293999312,
"count": 64007,
"is_parallel": true,
"self": 17.98574622606202,
"children": {
"_process_rank_one_or_two_observation": {
"total": 73.5483467139311,
"count": 512056,
"is_parallel": true,
"self": 73.5483467139311
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 655.6296358090485,
"count": 64008,
"self": 2.4288115320155157,
"children": {
"process_trajectory": {
"total": 119.74724932802474,
"count": 64008,
"self": 119.53791067002476,
"children": {
"RLTrainer._checkpoint": {
"total": 0.20933865799997875,
"count": 2,
"self": 0.20933865799997875
}
}
},
"_update_policy": {
"total": 533.4535749490083,
"count": 449,
"self": 298.28651095501255,
"children": {
"TorchPPOOptimizer.update": {
"total": 235.16706399399573,
"count": 22809,
"self": 235.16706399399573
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.420000424142927e-07,
"count": 1,
"self": 9.420000424142927e-07
},
"TrainerController._save_models": {
"total": 0.08175116600068577,
"count": 1,
"self": 0.001094154000384151,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08065701200030162,
"count": 1,
"self": 0.08065701200030162
}
}
}
}
}
}
}