Wanlin0001's picture
First Push
baaccd9
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.4804825782775879,
"min": 0.4804825782775879,
"max": 1.4100499153137207,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 14391.4140625,
"min": 14391.4140625,
"max": 42775.2734375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989912.0,
"min": 29903.0,
"max": 989912.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989912.0,
"min": 29903.0,
"max": 989912.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.21735306084156036,
"min": -0.1706910878419876,
"max": 0.21735306084156036,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 56.29444122314453,
"min": -40.45378875732422,
"max": 56.29444122314453,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.009009825065732002,
"min": -0.0020560743287205696,
"max": 0.23714423179626465,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 2.3335447311401367,
"min": -0.5119625329971313,
"max": 56.914615631103516,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06657327452280914,
"min": 0.06543433681217313,
"max": 0.07354671449103903,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.932025843319328,
"min": 0.5110623770938375,
"max": 1.0871179408271678,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.011643931672421916,
"min": 0.00020763309122278582,
"max": 0.011643931672421916,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.16301504341390682,
"min": 0.0024785553507887664,
"max": 0.16301504341390682,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.750768845014288e-06,
"min": 7.750768845014288e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010851076383020002,
"min": 0.00010851076383020002,
"max": 0.0035074736308422,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10258355714285713,
"min": 0.10258355714285713,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4361697999999998,
"min": 1.3886848,
"max": 2.5691578,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026809735857142864,
"min": 0.00026809735857142864,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0037533630200000012,
"min": 0.0037533630200000012,
"max": 0.11693886422000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.012323858216404915,
"min": 0.012323858216404915,
"max": 0.37931326031684875,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1725340187549591,
"min": 0.1725340187549591,
"max": 2.6551928520202637,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 582.9607843137255,
"min": 582.9607843137255,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29731.0,
"min": 16830.0,
"max": 31968.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 0.9463097777436761,
"min": -0.9999871489501768,
"max": 0.9463097777436761,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 48.26179866492748,
"min": -31.99920167028904,
"max": 48.26179866492748,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 0.9463097777436761,
"min": -0.9999871489501768,
"max": 0.9463097777436761,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 48.26179866492748,
"min": -31.99920167028904,
"max": 48.26179866492748,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.07504966162492101,
"min": 0.07504966162492101,
"max": 6.799671734080595,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.8275327428709716,
"min": 3.8275327428709716,
"max": 115.59441947937012,
"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": "1701103109",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1701105443"
},
"total": 2333.8360347869993,
"count": 1,
"self": 0.5332524309988003,
"children": {
"run_training.setup": {
"total": 0.05287358999976277,
"count": 1,
"self": 0.05287358999976277
},
"TrainerController.start_learning": {
"total": 2333.2499087660008,
"count": 1,
"self": 1.5637710619366771,
"children": {
"TrainerController._reset_env": {
"total": 3.112748071999704,
"count": 1,
"self": 3.112748071999704
},
"TrainerController.advance": {
"total": 2328.492467218064,
"count": 63373,
"self": 1.6420524990180638,
"children": {
"env_step": {
"total": 1645.8325345550875,
"count": 63373,
"self": 1500.9324014741414,
"children": {
"SubprocessEnvManager._take_step": {
"total": 143.9319800430394,
"count": 63373,
"self": 5.127772670118247,
"children": {
"TorchPolicy.evaluate": {
"total": 138.80420737292116,
"count": 62567,
"self": 138.80420737292116
}
}
},
"workers": {
"total": 0.9681530379066317,
"count": 63373,
"self": 0.0,
"children": {
"worker_root": {
"total": 2328.290248356905,
"count": 63373,
"is_parallel": true,
"self": 958.6353341397808,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001860268000200449,
"count": 1,
"is_parallel": true,
"self": 0.0006035989999872982,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012566690002131509,
"count": 8,
"is_parallel": true,
"self": 0.0012566690002131509
}
}
},
"UnityEnvironment.step": {
"total": 0.0496778369997628,
"count": 1,
"is_parallel": true,
"self": 0.0006118150004112977,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00048812800014275126,
"count": 1,
"is_parallel": true,
"self": 0.00048812800014275126
},
"communicator.exchange": {
"total": 0.04693746699922485,
"count": 1,
"is_parallel": true,
"self": 0.04693746699922485
},
"steps_from_proto": {
"total": 0.0016404269999839016,
"count": 1,
"is_parallel": true,
"self": 0.00036543799888022477,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012749890011036769,
"count": 8,
"is_parallel": true,
"self": 0.0012749890011036769
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1369.6549142171243,
"count": 63372,
"is_parallel": true,
"self": 35.24308782497519,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.005244279227554,
"count": 63372,
"is_parallel": true,
"self": 24.005244279227554
},
"communicator.exchange": {
"total": 1209.3860609429112,
"count": 63372,
"is_parallel": true,
"self": 1209.3860609429112
},
"steps_from_proto": {
"total": 101.0205211700104,
"count": 63372,
"is_parallel": true,
"self": 20.90280751299815,
"children": {
"_process_rank_one_or_two_observation": {
"total": 80.11771365701225,
"count": 506976,
"is_parallel": true,
"self": 80.11771365701225
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 681.0178801639586,
"count": 63373,
"self": 2.9919096208932388,
"children": {
"process_trajectory": {
"total": 133.43050422106717,
"count": 63373,
"self": 133.2624716780674,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1680325429997538,
"count": 2,
"self": 0.1680325429997538
}
}
},
"_update_policy": {
"total": 544.5954663219982,
"count": 445,
"self": 326.3352866579353,
"children": {
"TorchPPOOptimizer.update": {
"total": 218.2601796640629,
"count": 22797,
"self": 218.2601796640629
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.690002116258256e-07,
"count": 1,
"self": 9.690002116258256e-07
},
"TrainerController._save_models": {
"total": 0.08092144500005816,
"count": 1,
"self": 0.00125606500023423,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07966537999982393,
"count": 1,
"self": 0.07966537999982393
}
}
}
}
}
}
}