nardit's picture
Initial Commit
fe40d98 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9150812029838562,
"min": 0.9150812029838562,
"max": 2.842256784439087,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8696.931640625,
"min": 8696.931640625,
"max": 29013.7578125,
"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": 13.010574340820312,
"min": 0.42991551756858826,
"max": 13.030818939208984,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2537.06201171875,
"min": 83.40361022949219,
"max": 2658.287109375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0691646703595396,
"min": 0.06180336413329796,
"max": 0.07224683121296717,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2766586814381584,
"min": 0.24721345653319185,
"max": 0.3610760964425828,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20094781880285226,
"min": 0.12203604186766362,
"max": 0.2791001916516061,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.803791275211409,
"min": 0.4881441674706545,
"max": 1.2967385234786015,
"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": 25.386363636363637,
"min": 3.2954545454545454,
"max": 25.727272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1117.0,
"min": 145.0,
"max": 1410.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.386363636363637,
"min": 3.2954545454545454,
"max": 25.727272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1117.0,
"min": 145.0,
"max": 1410.0,
"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": "1752029479",
"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",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1752029907"
},
"total": 428.51494648999994,
"count": 1,
"self": 0.4399525689999564,
"children": {
"run_training.setup": {
"total": 0.029028957000036826,
"count": 1,
"self": 0.029028957000036826
},
"TrainerController.start_learning": {
"total": 428.04596496399995,
"count": 1,
"self": 0.3333392419924621,
"children": {
"TrainerController._reset_env": {
"total": 4.235058724000055,
"count": 1,
"self": 4.235058724000055
},
"TrainerController.advance": {
"total": 423.3933517060075,
"count": 18192,
"self": 0.3677373940273583,
"children": {
"env_step": {
"total": 304.2558170349896,
"count": 18192,
"self": 233.65235407198645,
"children": {
"SubprocessEnvManager._take_step": {
"total": 70.3924675119822,
"count": 18192,
"self": 1.260503753971193,
"children": {
"TorchPolicy.evaluate": {
"total": 69.13196375801101,
"count": 18192,
"self": 69.13196375801101
}
}
},
"workers": {
"total": 0.21099545102094908,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 426.6491880060081,
"count": 18192,
"is_parallel": true,
"self": 221.36061602600455,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006185687999959555,
"count": 1,
"is_parallel": true,
"self": 0.004134375999910844,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0020513120000487106,
"count": 10,
"is_parallel": true,
"self": 0.0020513120000487106
}
}
},
"UnityEnvironment.step": {
"total": 0.05633173599994734,
"count": 1,
"is_parallel": true,
"self": 0.0006009909999420415,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00039628299998639704,
"count": 1,
"is_parallel": true,
"self": 0.00039628299998639704
},
"communicator.exchange": {
"total": 0.053691899000000376,
"count": 1,
"is_parallel": true,
"self": 0.053691899000000376
},
"steps_from_proto": {
"total": 0.0016425630000185265,
"count": 1,
"is_parallel": true,
"self": 0.0003149310001617778,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013276319998567487,
"count": 10,
"is_parallel": true,
"self": 0.0013276319998567487
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 205.28857198000355,
"count": 18191,
"is_parallel": true,
"self": 9.999428244022965,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.462491352004804,
"count": 18191,
"is_parallel": true,
"self": 5.462491352004804
},
"communicator.exchange": {
"total": 157.4710052069688,
"count": 18191,
"is_parallel": true,
"self": 157.4710052069688
},
"steps_from_proto": {
"total": 32.35564717700697,
"count": 18191,
"is_parallel": true,
"self": 5.738347761022169,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.617299415984803,
"count": 181910,
"is_parallel": true,
"self": 26.617299415984803
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 118.76979727699052,
"count": 18192,
"self": 0.42386114998691937,
"children": {
"process_trajectory": {
"total": 25.67767647900405,
"count": 18192,
"self": 25.267534557003955,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4101419220000935,
"count": 4,
"self": 0.4101419220000935
}
}
},
"_update_policy": {
"total": 92.66825964799955,
"count": 90,
"self": 38.59870882599728,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.06955082200227,
"count": 4587,
"self": 54.06955082200227
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4459999420068925e-06,
"count": 1,
"self": 1.4459999420068925e-06
},
"TrainerController._save_models": {
"total": 0.08421384600001147,
"count": 1,
"self": 0.000855539999975008,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08335830600003646,
"count": 1,
"self": 0.08335830600003646
}
}
}
}
}
}
}