YCHuang2112's picture
First Push
888b116
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.42145341634750366,
"min": 0.42145341634750366,
"max": 1.4326130151748657,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 12771.724609375,
"min": 12701.3203125,
"max": 43459.75,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989973.0,
"min": 29952.0,
"max": 989973.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989973.0,
"min": 29952.0,
"max": 989973.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5038220882415771,
"min": -0.12523335218429565,
"max": 0.5038220882415771,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 135.52813720703125,
"min": -30.181236267089844,
"max": 135.52813720703125,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.006615536753088236,
"min": -0.02841763012111187,
"max": 0.39861464500427246,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 1.7795794010162354,
"min": -7.303330898284912,
"max": 94.47167205810547,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06918024013741939,
"min": 0.06564967001166132,
"max": 0.07221476849647408,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9685233619238715,
"min": 0.4852726584014044,
"max": 1.074504437216092,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015826694510733,
"min": 0.0007895647967996419,
"max": 0.016157230300854687,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.221573723150262,
"min": 0.006634679264335455,
"max": 0.24235845451282031,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.388411822942851e-06,
"min": 7.388411822942851e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010343776552119992,
"min": 0.00010343776552119992,
"max": 0.0032528990157003994,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10246277142857142,
"min": 0.10246277142857142,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4344788,
"min": 1.3691136000000002,
"max": 2.4009881999999996,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002560308657142856,
"min": 0.0002560308657142856,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0035844321199999985,
"min": 0.0035844321199999985,
"max": 0.10845153004,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.011213643476366997,
"min": 0.011047489941120148,
"max": 0.49090009927749634,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.15699100494384766,
"min": 0.15466485917568207,
"max": 3.436300754547119,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 385.5945945945946,
"min": 385.5945945945946,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28534.0,
"min": 15984.0,
"max": 33061.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5062621426139329,
"min": -1.0000000521540642,
"max": 1.5340903854533419,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 111.46339855343103,
"min": -32.000001668930054,
"max": 118.49959784001112,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5062621426139329,
"min": -1.0000000521540642,
"max": 1.5340903854533419,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 111.46339855343103,
"min": -32.000001668930054,
"max": 118.49959784001112,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.04563793744986273,
"min": 0.04563793744986273,
"max": 10.176431300118566,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.377207371289842,
"min": 3.1432292634999612,
"max": 162.82290080189705,
"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": "1685485320",
"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": "1685487549"
},
"total": 2228.6077259779995,
"count": 1,
"self": 0.4756453749996581,
"children": {
"run_training.setup": {
"total": 0.05538789000001998,
"count": 1,
"self": 0.05538789000001998
},
"TrainerController.start_learning": {
"total": 2228.076692713,
"count": 1,
"self": 1.5886882120216796,
"children": {
"TrainerController._reset_env": {
"total": 4.9803844019998,
"count": 1,
"self": 4.9803844019998
},
"TrainerController.advance": {
"total": 2221.4160484989784,
"count": 63597,
"self": 1.536859683957573,
"children": {
"env_step": {
"total": 1572.760144206994,
"count": 63597,
"self": 1452.8209737199595,
"children": {
"SubprocessEnvManager._take_step": {
"total": 118.99042204102807,
"count": 63597,
"self": 5.120379663048425,
"children": {
"TorchPolicy.evaluate": {
"total": 113.87004237797964,
"count": 62564,
"self": 113.87004237797964
}
}
},
"workers": {
"total": 0.9487484460064479,
"count": 63597,
"self": 0.0,
"children": {
"worker_root": {
"total": 2222.3603972771293,
"count": 63597,
"is_parallel": true,
"self": 892.418228541007,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0024964999997791892,
"count": 1,
"is_parallel": true,
"self": 0.0007229359998746077,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017735639999045816,
"count": 8,
"is_parallel": true,
"self": 0.0017735639999045816
}
}
},
"UnityEnvironment.step": {
"total": 0.04958534500019596,
"count": 1,
"is_parallel": true,
"self": 0.0005327960002432519,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005288329998620611,
"count": 1,
"is_parallel": true,
"self": 0.0005288329998620611
},
"communicator.exchange": {
"total": 0.04525357800002894,
"count": 1,
"is_parallel": true,
"self": 0.04525357800002894
},
"steps_from_proto": {
"total": 0.0032701380000617064,
"count": 1,
"is_parallel": true,
"self": 0.00036178000027575763,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0029083579997859488,
"count": 8,
"is_parallel": true,
"self": 0.0029083579997859488
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1329.9421687361223,
"count": 63596,
"is_parallel": true,
"self": 32.54623519695406,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.497587765069056,
"count": 63596,
"is_parallel": true,
"self": 24.497587765069056
},
"communicator.exchange": {
"total": 1166.6229346150171,
"count": 63596,
"is_parallel": true,
"self": 1166.6229346150171
},
"steps_from_proto": {
"total": 106.27541115908207,
"count": 63596,
"is_parallel": true,
"self": 22.36941604687945,
"children": {
"_process_rank_one_or_two_observation": {
"total": 83.90599511220262,
"count": 508768,
"is_parallel": true,
"self": 83.90599511220262
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 647.1190446080268,
"count": 63597,
"self": 2.748794996046854,
"children": {
"process_trajectory": {
"total": 113.99851507598987,
"count": 63597,
"self": 113.7919222229898,
"children": {
"RLTrainer._checkpoint": {
"total": 0.20659285300007468,
"count": 2,
"self": 0.20659285300007468
}
}
},
"_update_policy": {
"total": 530.3717345359901,
"count": 443,
"self": 343.17541114493997,
"children": {
"TorchPPOOptimizer.update": {
"total": 187.1963233910501,
"count": 22854,
"self": 187.1963233910501
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.890000001178123e-07,
"count": 1,
"self": 9.890000001178123e-07
},
"TrainerController._save_models": {
"total": 0.0915706109999519,
"count": 1,
"self": 0.0012433149995558779,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09032729600039602,
"count": 1,
"self": 0.09032729600039602
}
}
}
}
}
}
}