lee-910530's picture
First Push
ab08e1b verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.769005537033081,
"min": 0.769005537033081,
"max": 2.822814464569092,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7308.62890625,
"min": 7308.62890625,
"max": 28815.2890625,
"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": 12.953756332397461,
"min": 0.37616756558418274,
"max": 12.953756332397461,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2525.982421875,
"min": 72.97650909423828,
"max": 2620.16064453125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07425912513127852,
"min": 0.06159901993107233,
"max": 0.07465803815908015,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2970365005251141,
"min": 0.264382947895701,
"max": 0.35644431273434674,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20300209887471854,
"min": 0.11079711556507676,
"max": 0.2920391856893605,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8120083954988742,
"min": 0.44318846226030706,
"max": 1.3756512675215218,
"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": 25.727272727272727,
"min": 3.409090909090909,
"max": 25.763636363636362,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1132.0,
"min": 150.0,
"max": 1417.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.727272727272727,
"min": 3.409090909090909,
"max": 25.763636363636362,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1132.0,
"min": 150.0,
"max": 1417.0,
"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": "1747981604",
"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": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1747982039"
},
"total": 435.1610900520001,
"count": 1,
"self": 0.4312832860000526,
"children": {
"run_training.setup": {
"total": 0.023177946000032534,
"count": 1,
"self": 0.023177946000032534
},
"TrainerController.start_learning": {
"total": 434.70662882,
"count": 1,
"self": 0.35804019500119466,
"children": {
"TrainerController._reset_env": {
"total": 3.5787559169999668,
"count": 1,
"self": 3.5787559169999668
},
"TrainerController.advance": {
"total": 430.67947804399864,
"count": 18192,
"self": 0.39051334998566745,
"children": {
"env_step": {
"total": 307.4192421390038,
"count": 18192,
"self": 234.02177123600165,
"children": {
"SubprocessEnvManager._take_step": {
"total": 73.18304178800702,
"count": 18192,
"self": 1.322281901997826,
"children": {
"TorchPolicy.evaluate": {
"total": 71.86075988600919,
"count": 18192,
"self": 71.86075988600919
}
}
},
"workers": {
"total": 0.2144291149951414,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 433.23293656899443,
"count": 18192,
"is_parallel": true,
"self": 228.24626493298751,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0065537440000298375,
"count": 1,
"is_parallel": true,
"self": 0.005039078000095287,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015146659999345502,
"count": 10,
"is_parallel": true,
"self": 0.0015146659999345502
}
}
},
"UnityEnvironment.step": {
"total": 0.07273303199997372,
"count": 1,
"is_parallel": true,
"self": 0.0006775849998348349,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004038270000137345,
"count": 1,
"is_parallel": true,
"self": 0.0004038270000137345
},
"communicator.exchange": {
"total": 0.0698179150000442,
"count": 1,
"is_parallel": true,
"self": 0.0698179150000442
},
"steps_from_proto": {
"total": 0.001833705000080954,
"count": 1,
"is_parallel": true,
"self": 0.00036964800005989673,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014640570000210573,
"count": 10,
"is_parallel": true,
"self": 0.0014640570000210573
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 204.98667163600692,
"count": 18191,
"is_parallel": true,
"self": 9.968103919001692,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.607173118007836,
"count": 18191,
"is_parallel": true,
"self": 5.607173118007836
},
"communicator.exchange": {
"total": 157.0959834809961,
"count": 18191,
"is_parallel": true,
"self": 157.0959834809961
},
"steps_from_proto": {
"total": 32.31541111800129,
"count": 18191,
"is_parallel": true,
"self": 5.8966394139838485,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.418771704017445,
"count": 181910,
"is_parallel": true,
"self": 26.418771704017445
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 122.86972255500916,
"count": 18192,
"self": 0.47279260100208376,
"children": {
"process_trajectory": {
"total": 28.105780911006946,
"count": 18192,
"self": 27.67961242600711,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4261684849998346,
"count": 4,
"self": 0.4261684849998346
}
}
},
"_update_policy": {
"total": 94.29114904300013,
"count": 90,
"self": 37.95945134500175,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.33169769799838,
"count": 4587,
"self": 56.33169769799838
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0060000477096764e-06,
"count": 1,
"self": 1.0060000477096764e-06
},
"TrainerController._save_models": {
"total": 0.09035365800014006,
"count": 1,
"self": 0.0009080780002932443,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08944557999984681,
"count": 1,
"self": 0.08944557999984681
}
}
}
}
}
}
}