MichaelYxWang's picture
First Push
43c6d8b
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5565287470817566,
"min": 0.5430719256401062,
"max": 1.4449717998504639,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 16669.1484375,
"min": 16288.771484375,
"max": 43834.6640625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989933.0,
"min": 29898.0,
"max": 989933.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989933.0,
"min": 29898.0,
"max": 989933.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.09431148320436478,
"min": -0.09866420179605484,
"max": 0.1871734857559204,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 23.577871322631836,
"min": -23.67940902709961,
"max": 46.793373107910156,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.009372638538479805,
"min": 0.009372638538479805,
"max": 0.38267168402671814,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 2.3431596755981445,
"min": 2.3431596755981445,
"max": 90.69319152832031,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.0674020714283949,
"min": 0.06493550620088963,
"max": 0.07651386820940202,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9436289999975285,
"min": 0.5355970774658142,
"max": 1.029468294485317,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.008129203296089184,
"min": 0.00014725717992392586,
"max": 0.009162062218826183,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.11380884614524858,
"min": 0.001914343339011036,
"max": 0.11814203133875638,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.66130458912143e-06,
"min": 7.66130458912143e-06,
"max": 0.0002952352301596857,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010725826424770002,
"min": 0.00010725826424770002,
"max": 0.0036334303888565997,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10255373571428572,
"min": 0.10255373571428572,
"max": 0.19841174285714283,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4357523,
"min": 1.3888821999999998,
"max": 2.6111433999999996,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002651181978571429,
"min": 0.0002651181978571429,
"max": 0.00984133311142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0037116547700000004,
"min": 0.0037116547700000004,
"max": 0.12113322566000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.014978128485381603,
"min": 0.014978128485381603,
"max": 0.5412553548812866,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.2096938043832779,
"min": 0.2096938043832779,
"max": 3.788787364959717,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 740.9024390243902,
"min": 657.0,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30377.0,
"min": 16569.0,
"max": 32676.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 0.47834629928920325,
"min": -0.9998516647085067,
"max": 0.7044850667106345,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 19.612198270857334,
"min": -31.994001656770706,
"max": 33.11079813539982,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 0.47834629928920325,
"min": -0.9998516647085067,
"max": 0.7044850667106345,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 19.612198270857334,
"min": -31.994001656770706,
"max": 33.11079813539982,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.11506498127710074,
"min": 0.11077069833582426,
"max": 10.440576157149147,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.71766423236113,
"min": 4.6323838075913955,
"max": 177.4897946715355,
"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": "1692084467",
"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": "1692087284"
},
"total": 2816.8065292849997,
"count": 1,
"self": 1.0348494159993606,
"children": {
"run_training.setup": {
"total": 0.04553028100008305,
"count": 1,
"self": 0.04553028100008305
},
"TrainerController.start_learning": {
"total": 2815.726149588,
"count": 1,
"self": 2.3151759990414575,
"children": {
"TrainerController._reset_env": {
"total": 4.542189540999971,
"count": 1,
"self": 4.542189540999971
},
"TrainerController.advance": {
"total": 2808.679381603959,
"count": 63316,
"self": 2.1977850719285925,
"children": {
"env_step": {
"total": 2013.401046071988,
"count": 63316,
"self": 1850.3693109118983,
"children": {
"SubprocessEnvManager._take_step": {
"total": 161.63515073500616,
"count": 63316,
"self": 6.562004265080077,
"children": {
"TorchPolicy.evaluate": {
"total": 155.0731464699261,
"count": 62557,
"self": 155.0731464699261
}
}
},
"workers": {
"total": 1.3965844250835744,
"count": 63316,
"self": 0.0,
"children": {
"worker_root": {
"total": 2808.491953999994,
"count": 63316,
"is_parallel": true,
"self": 1122.475752722131,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0019934160000047996,
"count": 1,
"is_parallel": true,
"self": 0.0006474679996699706,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001345948000334829,
"count": 8,
"is_parallel": true,
"self": 0.001345948000334829
}
}
},
"UnityEnvironment.step": {
"total": 0.0554297090000091,
"count": 1,
"is_parallel": true,
"self": 0.0006829469998592685,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005878790000224399,
"count": 1,
"is_parallel": true,
"self": 0.0005878790000224399
},
"communicator.exchange": {
"total": 0.05190482700004395,
"count": 1,
"is_parallel": true,
"self": 0.05190482700004395
},
"steps_from_proto": {
"total": 0.0022540560000834375,
"count": 1,
"is_parallel": true,
"self": 0.00043566000067585264,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001818395999407585,
"count": 8,
"is_parallel": true,
"self": 0.001818395999407585
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1686.0162012778633,
"count": 63315,
"is_parallel": true,
"self": 43.90390126877196,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 30.08598225305218,
"count": 63315,
"is_parallel": true,
"self": 30.08598225305218
},
"communicator.exchange": {
"total": 1468.7930018900147,
"count": 63315,
"is_parallel": true,
"self": 1468.7930018900147
},
"steps_from_proto": {
"total": 143.23331586602444,
"count": 63315,
"is_parallel": true,
"self": 29.864077754878508,
"children": {
"_process_rank_one_or_two_observation": {
"total": 113.36923811114593,
"count": 506520,
"is_parallel": true,
"self": 113.36923811114593
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 793.0805504600426,
"count": 63316,
"self": 4.0975665110768205,
"children": {
"process_trajectory": {
"total": 144.11364085696573,
"count": 63316,
"self": 143.79065141396563,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3229894430000968,
"count": 2,
"self": 0.3229894430000968
}
}
},
"_update_policy": {
"total": 644.869343092,
"count": 455,
"self": 418.1995016319802,
"children": {
"TorchPPOOptimizer.update": {
"total": 226.66984146001982,
"count": 22755,
"self": 226.66984146001982
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.5799996617715806e-06,
"count": 1,
"self": 1.5799996617715806e-06
},
"TrainerController._save_models": {
"total": 0.18940086400016298,
"count": 1,
"self": 0.002414128000054916,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18698673600010807,
"count": 1,
"self": 0.18698673600010807
}
}
}
}
}
}
}