marcus07's picture
First Push
ff00502 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7754722833633423,
"min": 0.7657526135444641,
"max": 2.8711438179016113,
"count": 50
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7506.57177734375,
"min": 7277.712890625,
"max": 29403.3828125,
"count": 50
},
"SnowballTarget.Step.mean": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Step.sum": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.606134414672852,
"min": 0.3890088200569153,
"max": 13.722529411315918,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2789.257568359375,
"min": 75.46771240234375,
"max": 2799.39599609375,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06538191351494022,
"min": 0.06220048081555504,
"max": 0.07803483618886722,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3269095675747011,
"min": 0.24880192326222017,
"max": 0.36883155694322695,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18201290512201834,
"min": 0.11943581322203482,
"max": 0.2981918522101991,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9100645256100917,
"min": 0.4777432528881393,
"max": 1.3902910865989386,
"count": 50
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 3.0528989824000028e-06,
"min": 3.0528989824000028e-06,
"max": 0.00029675280108239997,
"count": 50
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.5264494912000015e-05,
"min": 1.5264494912000015e-05,
"max": 0.001454064015312,
"count": 50
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10101760000000001,
"min": 0.10101760000000001,
"max": 0.19891759999999997,
"count": 50
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.5050880000000001,
"min": 0.41199040000000003,
"max": 0.984688,
"count": 50
},
"SnowballTarget.Policy.Beta.mean": {
"value": 6.0778240000000044e-05,
"min": 6.0778240000000044e-05,
"max": 0.00494598824,
"count": 50
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0003038912000000002,
"min": 0.0003038912000000002,
"max": 0.0242359312,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.254545454545454,
"min": 3.4318181818181817,
"max": 27.145454545454545,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1444.0,
"min": 151.0,
"max": 1493.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.254545454545454,
"min": 3.4318181818181817,
"max": 27.145454545454545,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1444.0,
"min": 151.0,
"max": 1493.0,
"count": 50
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1714562244",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1714563411"
},
"total": 1166.6966391229998,
"count": 1,
"self": 0.44238212100003693,
"children": {
"run_training.setup": {
"total": 0.05772473499996522,
"count": 1,
"self": 0.05772473499996522
},
"TrainerController.start_learning": {
"total": 1166.1965322669998,
"count": 1,
"self": 1.394253988980381,
"children": {
"TrainerController._reset_env": {
"total": 2.7503450049999856,
"count": 1,
"self": 2.7503450049999856
},
"TrainerController.advance": {
"total": 1161.9619085960192,
"count": 45473,
"self": 0.7203130979917205,
"children": {
"env_step": {
"total": 1161.2415954980274,
"count": 45473,
"self": 752.3691589549815,
"children": {
"SubprocessEnvManager._take_step": {
"total": 408.1283050980237,
"count": 45473,
"self": 4.090393263988972,
"children": {
"TorchPolicy.evaluate": {
"total": 404.03791183403473,
"count": 45473,
"self": 404.03791183403473
}
}
},
"workers": {
"total": 0.7441314450222762,
"count": 45473,
"self": 0.0,
"children": {
"worker_root": {
"total": 1163.14613647302,
"count": 45473,
"is_parallel": true,
"self": 579.8086245110172,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005242626000040218,
"count": 1,
"is_parallel": true,
"self": 0.003626690000146482,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016159359998937362,
"count": 10,
"is_parallel": true,
"self": 0.0016159359998937362
}
}
},
"UnityEnvironment.step": {
"total": 0.04481413300004533,
"count": 1,
"is_parallel": true,
"self": 0.0021169469999904322,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000408078000077694,
"count": 1,
"is_parallel": true,
"self": 0.000408078000077694
},
"communicator.exchange": {
"total": 0.04011978699998053,
"count": 1,
"is_parallel": true,
"self": 0.04011978699998053
},
"steps_from_proto": {
"total": 0.002169320999996671,
"count": 1,
"is_parallel": true,
"self": 0.00043197400009375997,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017373469999029112,
"count": 10,
"is_parallel": true,
"self": 0.0017373469999029112
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 583.3375119620028,
"count": 45472,
"is_parallel": true,
"self": 26.57459214304015,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 14.553109399001073,
"count": 45472,
"is_parallel": true,
"self": 14.553109399001073
},
"communicator.exchange": {
"total": 451.7761595199755,
"count": 45472,
"is_parallel": true,
"self": 451.7761595199755
},
"steps_from_proto": {
"total": 90.4336508999861,
"count": 45472,
"is_parallel": true,
"self": 16.97052263493765,
"children": {
"_process_rank_one_or_two_observation": {
"total": 73.46312826504845,
"count": 454720,
"is_parallel": true,
"self": 73.46312826504845
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00014010500012773264,
"count": 1,
"self": 0.00014010500012773264,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 1146.897774661027,
"count": 1760735,
"is_parallel": true,
"self": 38.388327626931186,
"children": {
"process_trajectory": {
"total": 632.6697963490964,
"count": 1760735,
"is_parallel": true,
"self": 631.2122672960967,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4575290529996892,
"count": 11,
"is_parallel": true,
"self": 1.4575290529996892
}
}
},
"_update_policy": {
"total": 475.83965068499936,
"count": 227,
"is_parallel": true,
"self": 139.78062287798855,
"children": {
"TorchPPOOptimizer.update": {
"total": 336.0590278070108,
"count": 11574,
"is_parallel": true,
"self": 336.0590278070108
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.0898845720000736,
"count": 1,
"self": 0.0009937120000813593,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08889085999999224,
"count": 1,
"self": 0.08889085999999224
}
}
}
}
}
}
}