RBadal's picture
First Push
18712ce verified
Raw
History Blame Contribute Delete
17.6 kB
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9200097322463989,
"min": 0.9200097322463989,
"max": 2.854032516479492,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8743.7724609375,
"min": 8743.7724609375,
"max": 29133.96484375,
"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": 11.696769714355469,
"min": 0.34838905930519104,
"max": 11.696769714355469,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2280.8701171875,
"min": 67.58747863769531,
"max": 2366.86181640625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06804411608112894,
"min": 0.05903461868836209,
"max": 0.07340686155848922,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27217646432451575,
"min": 0.23613847475344835,
"max": 0.36703430779244606,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18299365708348797,
"min": 0.13800449131682113,
"max": 0.29800323835190606,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7319746283339519,
"min": 0.5520179652672845,
"max": 1.3897145232733559,
"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": 23.272727272727273,
"min": 4.090909090909091,
"max": 23.272727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1024.0,
"min": 180.0,
"max": 1270.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.272727272727273,
"min": 4.090909090909091,
"max": 23.272727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1024.0,
"min": 180.0,
"max": 1270.0,
"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": "1784181617",
"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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1784182123"
},
"total": 505.79250960699983,
"count": 1,
"self": 0.43312800600006085,
"children": {
"run_training.setup": {
"total": 0.028902558999789107,
"count": 1,
"self": 0.028902558999789107
},
"TrainerController.start_learning": {
"total": 505.330479042,
"count": 1,
"self": 0.42412168801547523,
"children": {
"TrainerController._reset_env": {
"total": 3.154310572999975,
"count": 1,
"self": 3.154310572999975
},
"TrainerController.advance": {
"total": 501.6644593739845,
"count": 18192,
"self": 0.4397926019703391,
"children": {
"env_step": {
"total": 372.10193301300774,
"count": 18192,
"self": 292.75279636602386,
"children": {
"SubprocessEnvManager._take_step": {
"total": 79.09916493099308,
"count": 18192,
"self": 1.4127097029943343,
"children": {
"TorchPolicy.evaluate": {
"total": 77.68645522799875,
"count": 18192,
"self": 77.68645522799875
}
}
},
"workers": {
"total": 0.24997171599079593,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 503.3125478889913,
"count": 18192,
"is_parallel": true,
"self": 245.96128097600035,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0052560149999862915,
"count": 1,
"is_parallel": true,
"self": 0.00372844000025907,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015275749997272214,
"count": 10,
"is_parallel": true,
"self": 0.0015275749997272214
}
}
},
"UnityEnvironment.step": {
"total": 0.041194250999978976,
"count": 1,
"is_parallel": true,
"self": 0.0006891139998970175,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00048404799986201397,
"count": 1,
"is_parallel": true,
"self": 0.00048404799986201397
},
"communicator.exchange": {
"total": 0.037918204000106925,
"count": 1,
"is_parallel": true,
"self": 0.037918204000106925
},
"steps_from_proto": {
"total": 0.0021028850001130195,
"count": 1,
"is_parallel": true,
"self": 0.00041357700001753983,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016893080000954797,
"count": 10,
"is_parallel": true,
"self": 0.0016893080000954797
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 257.3512669129909,
"count": 18191,
"is_parallel": true,
"self": 11.355288854008222,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.100504444990747,
"count": 18191,
"is_parallel": true,
"self": 6.100504444990747
},
"communicator.exchange": {
"total": 197.37792030899345,
"count": 18191,
"is_parallel": true,
"self": 197.37792030899345
},
"steps_from_proto": {
"total": 42.5175533049985,
"count": 18191,
"is_parallel": true,
"self": 7.403453633925665,
"children": {
"_process_rank_one_or_two_observation": {
"total": 35.114099671072836,
"count": 181910,
"is_parallel": true,
"self": 35.114099671072836
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 129.12273375900645,
"count": 18192,
"self": 0.5086383690063485,
"children": {
"process_trajectory": {
"total": 26.547777332999658,
"count": 18192,
"self": 26.065034663999768,
"children": {
"RLTrainer._checkpoint": {
"total": 0.48274266899989016,
"count": 4,
"self": 0.48274266899989016
}
}
},
"_update_policy": {
"total": 102.06631805700044,
"count": 90,
"self": 41.790138431982996,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.27617962501745,
"count": 4587,
"self": 60.27617962501745
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0490000477147987e-06,
"count": 1,
"self": 1.0490000477147987e-06
},
"TrainerController._save_models": {
"total": 0.08758635799995318,
"count": 1,
"self": 0.0007865439999932278,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08679981399995995,
"count": 1,
"self": 0.08679981399995995
}
}
}
}
}
}
}