txia-m's picture
First Push
bf42d50 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9647424221038818,
"min": 0.9647424221038818,
"max": 2.852292537689209,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9168.912109375,
"min": 9168.912109375,
"max": 29116.203125,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.074374198913574,
"min": 0.4058115482330322,
"max": 13.074374198913574,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2549.5029296875,
"min": 78.7274398803711,
"max": 2639.6416015625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06578629772511527,
"min": 0.06230112632700041,
"max": 0.07071397200343199,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26314519090046107,
"min": 0.25124527043868405,
"max": 0.3535213580855725,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2195542730829295,
"min": 0.1465723047046648,
"max": 0.31227850271206276,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.878217092331718,
"min": 0.5862892188186593,
"max": 1.5613925135603137,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.636363636363637,
"min": 3.840909090909091,
"max": 25.672727272727272,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1128.0,
"min": 169.0,
"max": 1412.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.636363636363637,
"min": 3.840909090909091,
"max": 25.672727272727272,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1128.0,
"min": 169.0,
"max": 1412.0,
"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": "1767663616",
"python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1767664050"
},
"total": 434.19279350399995,
"count": 1,
"self": 0.43070262199989884,
"children": {
"run_training.setup": {
"total": 0.0249507460000018,
"count": 1,
"self": 0.0249507460000018
},
"TrainerController.start_learning": {
"total": 433.73714013600005,
"count": 1,
"self": 0.32546118199513785,
"children": {
"TrainerController._reset_env": {
"total": 3.190408082000033,
"count": 1,
"self": 3.190408082000033
},
"TrainerController.advance": {
"total": 430.13139969000486,
"count": 18192,
"self": 0.35726455201938734,
"children": {
"env_step": {
"total": 309.4588992449891,
"count": 18192,
"self": 241.96975345898505,
"children": {
"SubprocessEnvManager._take_step": {
"total": 67.28056108299751,
"count": 18192,
"self": 1.2311747749857886,
"children": {
"TorchPolicy.evaluate": {
"total": 66.04938630801172,
"count": 18192,
"self": 66.04938630801172
}
}
},
"workers": {
"total": 0.20858470300652243,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 431.98740266700383,
"count": 18192,
"is_parallel": true,
"self": 219.43064278501282,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.008256227000003946,
"count": 1,
"is_parallel": true,
"self": 0.006718204999970112,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001538022000033834,
"count": 10,
"is_parallel": true,
"self": 0.001538022000033834
}
}
},
"UnityEnvironment.step": {
"total": 0.03718142099995703,
"count": 1,
"is_parallel": true,
"self": 0.0006229769999777091,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004663219999656576,
"count": 1,
"is_parallel": true,
"self": 0.0004663219999656576
},
"communicator.exchange": {
"total": 0.03406152200000179,
"count": 1,
"is_parallel": true,
"self": 0.03406152200000179
},
"steps_from_proto": {
"total": 0.002030600000011873,
"count": 1,
"is_parallel": true,
"self": 0.0004185630000392848,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001612036999972588,
"count": 10,
"is_parallel": true,
"self": 0.001612036999972588
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 212.556759881991,
"count": 18191,
"is_parallel": true,
"self": 10.183331402006843,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.258071837990997,
"count": 18191,
"is_parallel": true,
"self": 5.258071837990997
},
"communicator.exchange": {
"total": 161.64304122299882,
"count": 18191,
"is_parallel": true,
"self": 161.64304122299882
},
"steps_from_proto": {
"total": 35.472315418994356,
"count": 18191,
"is_parallel": true,
"self": 6.449235357993189,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.023080061001167,
"count": 181910,
"is_parallel": true,
"self": 29.023080061001167
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 120.31523589299638,
"count": 18192,
"self": 0.42376034000074014,
"children": {
"process_trajectory": {
"total": 26.31143385699528,
"count": 18192,
"self": 25.775970630995232,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5354632260000471,
"count": 4,
"self": 0.5354632260000471
}
}
},
"_update_policy": {
"total": 93.58004169600036,
"count": 90,
"self": 38.42148115099735,
"children": {
"TorchPPOOptimizer.update": {
"total": 55.15856054500301,
"count": 4587,
"self": 55.15856054500301
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2110000398024567e-06,
"count": 1,
"self": 1.2110000398024567e-06
},
"TrainerController._save_models": {
"total": 0.08986997099998462,
"count": 1,
"self": 0.0006340339999724165,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0892359370000122,
"count": 1,
"self": 0.0892359370000122
}
}
}
}
}
}
}