HibaST's picture
Push
a44638e verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.3752208948135376,
"min": 1.3752208948135376,
"max": 2.8792243003845215,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7019.12744140625,
"min": 6500.197265625,
"max": 14695.560546875,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 99960.0,
"min": 4976.0,
"max": 99960.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 99960.0,
"min": 4976.0,
"max": 99960.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 10.686447143554688,
"min": 0.07361346483230591,
"max": 10.686447143554688,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1036.5853271484375,
"min": 7.140506267547607,
"max": 1123.251953125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06302493172709137,
"min": 0.060685857383742034,
"max": 0.07596640078140898,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.12604986345418273,
"min": 0.12137171476748407,
"max": 0.22474944917713385,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2708837576940948,
"min": 0.10067576895851423,
"max": 0.31874683367855405,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.5417675153881896,
"min": 0.20135153791702845,
"max": 0.9013772790922838,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 6.564097812000004e-06,
"min": 6.564097812000004e-06,
"max": 0.000290364003212,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.3128195624000008e-05,
"min": 1.3128195624000008e-05,
"max": 0.000742392052536,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10218800000000001,
"min": 0.10218800000000001,
"max": 0.19678800000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.20437600000000003,
"min": 0.20437600000000003,
"max": 0.547464,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00011918120000000008,
"min": 0.00011918120000000008,
"max": 0.0048397212,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00023836240000000016,
"min": 0.00023836240000000016,
"max": 0.012378453600000002,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 4378.0,
"min": 4378.0,
"max": 6567.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 22.818181818181817,
"min": 2.4545454545454546,
"max": 22.818181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 502.0,
"min": 54.0,
"max": 725.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 22.818181818181817,
"min": 2.4545454545454546,
"max": 22.818181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 502.0,
"min": 54.0,
"max": 725.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1744037760",
"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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1744038042"
},
"total": 281.903147904,
"count": 1,
"self": 0.5345222400001148,
"children": {
"run_training.setup": {
"total": 0.03393595599982291,
"count": 1,
"self": 0.03393595599982291
},
"TrainerController.start_learning": {
"total": 281.33468970800004,
"count": 1,
"self": 0.297205634022248,
"children": {
"TrainerController._reset_env": {
"total": 2.958993692999684,
"count": 1,
"self": 2.958993692999684
},
"TrainerController.advance": {
"total": 277.9517094909779,
"count": 9128,
"self": 0.3209863119691363,
"children": {
"env_step": {
"total": 191.080019893996,
"count": 9128,
"self": 160.9206809839343,
"children": {
"SubprocessEnvManager._take_step": {
"total": 29.981188425026176,
"count": 9128,
"self": 1.0280603210212576,
"children": {
"TorchPolicy.evaluate": {
"total": 28.953128104004918,
"count": 9128,
"self": 28.953128104004918
}
}
},
"workers": {
"total": 0.17815048503553044,
"count": 9128,
"self": 0.0,
"children": {
"worker_root": {
"total": 280.00207520498907,
"count": 9128,
"is_parallel": true,
"self": 141.3386076509646,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003488911999738775,
"count": 1,
"is_parallel": true,
"self": 0.0010046499996860803,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002484262000052695,
"count": 10,
"is_parallel": true,
"self": 0.002484262000052695
}
}
},
"UnityEnvironment.step": {
"total": 0.08540399899993645,
"count": 1,
"is_parallel": true,
"self": 0.0006688529997518344,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004942169998685131,
"count": 1,
"is_parallel": true,
"self": 0.0004942169998685131
},
"communicator.exchange": {
"total": 0.08211564400016869,
"count": 1,
"is_parallel": true,
"self": 0.08211564400016869
},
"steps_from_proto": {
"total": 0.0021252850001474144,
"count": 1,
"is_parallel": true,
"self": 0.0004290730003049248,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016962119998424896,
"count": 10,
"is_parallel": true,
"self": 0.0016962119998424896
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 138.66346755402446,
"count": 9127,
"is_parallel": true,
"self": 6.582037075058906,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 3.602298950992008,
"count": 9127,
"is_parallel": true,
"self": 3.602298950992008
},
"communicator.exchange": {
"total": 108.36501480700053,
"count": 9127,
"is_parallel": true,
"self": 108.36501480700053
},
"steps_from_proto": {
"total": 20.114116720973016,
"count": 9127,
"is_parallel": true,
"self": 4.061979567959497,
"children": {
"_process_rank_one_or_two_observation": {
"total": 16.05213715301352,
"count": 91270,
"is_parallel": true,
"self": 16.05213715301352
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 86.55070328501279,
"count": 9128,
"self": 0.38456874204575797,
"children": {
"process_trajectory": {
"total": 24.10928821096786,
"count": 9128,
"self": 22.6672349959681,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4420532149997598,
"count": 10,
"self": 1.4420532149997598
}
}
},
"_update_policy": {
"total": 62.05684633199917,
"count": 45,
"self": 23.125513341992246,
"children": {
"TorchPPOOptimizer.update": {
"total": 38.93133299000692,
"count": 2292,
"self": 38.93133299000692
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.5740001799713355e-06,
"count": 1,
"self": 1.5740001799713355e-06
},
"TrainerController._save_models": {
"total": 0.12677931600001102,
"count": 1,
"self": 0.0018980419999934384,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12488127400001758,
"count": 1,
"self": 0.12488127400001758
}
}
}
}
}
}
}