c-bone's picture
First Push
87ecbb0 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.205276370048523,
"min": 1.205276370048523,
"max": 2.89025616645813,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 11454.9462890625,
"min": 11454.9462890625,
"max": 29704.525390625,
"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": 7.596075534820557,
"min": 0.35176125168800354,
"max": 7.633275508880615,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1481.2347412109375,
"min": 68.24168395996094,
"max": 1536.40234375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.044307378024313955,
"min": 0.03895976755696514,
"max": 0.05071929231756561,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.17722951209725582,
"min": 0.15583907022786056,
"max": 0.25359646158782806,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.30866156161452335,
"min": 0.11381030695823333,
"max": 0.30866156161452335,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 1.2346462464580934,
"min": 0.4552412278329333,
"max": 1.5253208621094625,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 2.694097306000002e-06,
"min": 2.694097306000002e-06,
"max": 9.7294002706e-05,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.0776389224000008e-05,
"min": 1.0776389224000008e-05,
"max": 0.00046172003828,
"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": 0.9617200000000001,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00014443060000000012,
"min": 0.00014443060000000012,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000005,
"min": 0.0005777224000000005,
"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": 14.818181818181818,
"min": 2.727272727272727,
"max": 15.227272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 652.0,
"min": 120.0,
"max": 820.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 14.818181818181818,
"min": 2.727272727272727,
"max": 15.227272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 652.0,
"min": 120.0,
"max": 820.0,
"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": "1744640547",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1744640963"
},
"total": 415.41727401,
"count": 1,
"self": 0.4374012780000385,
"children": {
"run_training.setup": {
"total": 0.02492259500002092,
"count": 1,
"self": 0.02492259500002092
},
"TrainerController.start_learning": {
"total": 414.95495013699997,
"count": 1,
"self": 0.4133229269995127,
"children": {
"TrainerController._reset_env": {
"total": 2.9174646780001012,
"count": 1,
"self": 2.9174646780001012
},
"TrainerController.advance": {
"total": 411.53388932500025,
"count": 18192,
"self": 0.4079416080066949,
"children": {
"env_step": {
"total": 313.7793766109959,
"count": 18192,
"self": 238.27774353701432,
"children": {
"SubprocessEnvManager._take_step": {
"total": 75.27376292799158,
"count": 18192,
"self": 1.3559017369889261,
"children": {
"TorchPolicy.evaluate": {
"total": 73.91786119100266,
"count": 18192,
"self": 73.91786119100266
}
}
},
"workers": {
"total": 0.22787014598998212,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 413.4660677529956,
"count": 18192,
"is_parallel": true,
"self": 205.10035913199488,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005962388000057217,
"count": 1,
"is_parallel": true,
"self": 0.004298509000250306,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016638789998069115,
"count": 10,
"is_parallel": true,
"self": 0.0016638789998069115
}
}
},
"UnityEnvironment.step": {
"total": 0.03655658799993944,
"count": 1,
"is_parallel": true,
"self": 0.0006204750000051718,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00038453899992418883,
"count": 1,
"is_parallel": true,
"self": 0.00038453899992418883
},
"communicator.exchange": {
"total": 0.033629256000040186,
"count": 1,
"is_parallel": true,
"self": 0.033629256000040186
},
"steps_from_proto": {
"total": 0.0019223179999698914,
"count": 1,
"is_parallel": true,
"self": 0.0003794249998918531,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015428930000780383,
"count": 10,
"is_parallel": true,
"self": 0.0015428930000780383
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 208.36570862100075,
"count": 18191,
"is_parallel": true,
"self": 10.059167335983147,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.5534673350028925,
"count": 18191,
"is_parallel": true,
"self": 5.5534673350028925
},
"communicator.exchange": {
"total": 159.73285450500498,
"count": 18191,
"is_parallel": true,
"self": 159.73285450500498
},
"steps_from_proto": {
"total": 33.02021944500973,
"count": 18191,
"is_parallel": true,
"self": 6.043992789055778,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.97622665595395,
"count": 181910,
"is_parallel": true,
"self": 26.97622665595395
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 97.34657110599767,
"count": 18192,
"self": 0.4837035279887232,
"children": {
"process_trajectory": {
"total": 28.536882370008016,
"count": 18192,
"self": 28.08196475800787,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4549176120001448,
"count": 4,
"self": 0.4549176120001448
}
}
},
"_update_policy": {
"total": 68.32598520800093,
"count": 90,
"self": 37.42559140100195,
"children": {
"TorchPPOOptimizer.update": {
"total": 30.900393806998977,
"count": 2160,
"self": 30.900393806998977
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.81000005392707e-07,
"count": 1,
"self": 8.81000005392707e-07
},
"TrainerController._save_models": {
"total": 0.09027232600010393,
"count": 1,
"self": 0.0007102440001744981,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08956208199992943,
"count": 1,
"self": 0.08956208199992943
}
}
}
}
}
}
}