{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9059309363365173, "min": 0.9059309363365173, "max": 2.8218741416931152, "count": 10 }, "SnowballTarget.Policy.Entropy.sum": { "value": 17927.466796875, "min": 17927.466796875, "max": 58045.953125, "count": 10 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 19992.0, "max": 199984.0, "count": 10 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 19992.0, "max": 199984.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.104545593261719, "min": 0.6539127826690674, "max": 13.104545593261719, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 5228.7138671875, "min": 260.91119384765625, "max": 5228.7138671875, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 19701.0, "min": 19701.0, "max": 19701.0, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06959990624930357, "min": 0.06547574243621271, "max": 0.07339285991189422, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.6263991562437321, "min": 0.5892816819259143, "max": 0.660535739207048, "count": 10 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20983186302491522, "min": 0.15744856274524432, "max": 0.281030580758529, "count": 10 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.888486767224237, "min": 1.4170370647071988, "max": 2.529275226826761, "count": 10 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.6332094556000002e-05, "min": 1.6332094556000002e-05, "max": 0.00028363200545599993, "count": 10 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.000146988851004, "min": 0.000146988851004, "max": 0.0025526880491039995, "count": 10 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10544400000000001, "min": 0.10544400000000001, "max": 0.19454400000000002, "count": 10 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.9489960000000001, "min": 0.9489960000000001, "max": 1.7508960000000002, "count": 10 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00028165560000000005, "min": 0.00028165560000000005, "max": 0.0047277456, "count": 10 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0025349004000000007, "min": 0.0025349004000000007, "max": 0.0425497104, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.606060606060606, "min": 4.808080808080808, "max": 25.828282828282827, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 2535.0, "min": 476.0, "max": 2557.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.606060606060606, "min": 4.808080808080808, "max": 25.828282828282827, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 2535.0, "min": 476.0, "max": 2557.0, "count": 10 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1678693800", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1678694498" }, "total": 698.486242081, "count": 1, "self": 0.7064504140000736, "children": { "run_training.setup": { "total": 0.2220008109999867, "count": 1, "self": 0.2220008109999867 }, "TrainerController.start_learning": { "total": 697.557790856, "count": 1, "self": 1.0026535199973523, "children": { "TrainerController._reset_env": { "total": 6.826679038000009, "count": 1, "self": 6.826679038000009 }, "TrainerController.advance": { "total": 689.5578237660028, "count": 18202, "self": 0.5272575480104251, "children": { "env_step": { "total": 689.0305662179924, "count": 18202, "self": 556.3805058329876, "children": { "SubprocessEnvManager._take_step": { "total": 132.1503171209991, "count": 18202, "self": 5.1227913849939455, "children": { "TorchPolicy.evaluate": { "total": 127.02752573600515, "count": 18202, "self": 127.02752573600515 } } }, "workers": { "total": 0.4997432640056445, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 694.8355583180095, "count": 18202, "is_parallel": true, "self": 308.9843949229972, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007334834999994655, "count": 1, "is_parallel": true, "self": 0.0054120850001027065, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019227499998919484, "count": 10, "is_parallel": true, "self": 0.0019227499998919484 } } }, "UnityEnvironment.step": { "total": 0.09686668399996279, "count": 1, "is_parallel": true, "self": 0.0009361209999951825, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005157519999556825, "count": 1, "is_parallel": true, "self": 0.0005157519999556825 }, "communicator.exchange": { "total": 0.09276901800001269, "count": 1, "is_parallel": true, "self": 0.09276901800001269 }, "steps_from_proto": { "total": 0.0026457929999992302, "count": 1, "is_parallel": true, "self": 0.000743652000039674, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019021409999595562, "count": 10, "is_parallel": true, "self": 0.0019021409999595562 } } } } } } }, "UnityEnvironment.step": { "total": 385.8511633950123, "count": 18201, "is_parallel": true, "self": 15.955175952008574, "children": { "UnityEnvironment._generate_step_input": { "total": 8.179617947002725, "count": 18201, "is_parallel": true, "self": 8.179617947002725 }, "communicator.exchange": { "total": 311.6394226209971, "count": 18201, "is_parallel": true, "self": 311.6394226209971 }, "steps_from_proto": { "total": 50.0769468750039, "count": 18201, "is_parallel": true, "self": 10.864940795009488, "children": { "_process_rank_one_or_two_observation": { "total": 39.21200607999441, "count": 182010, "is_parallel": true, "self": 39.21200607999441 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0002027819999739222, "count": 1, "self": 0.0002027819999739222, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 682.479013100006, "count": 706317, "is_parallel": true, "self": 20.226990178014034, "children": { "process_trajectory": { "total": 373.54394379999155, "count": 706317, "is_parallel": true, "self": 371.38178160099153, "children": { "RLTrainer._checkpoint": { "total": 2.162162199000022, "count": 4, "is_parallel": true, "self": 2.162162199000022 } } }, "_update_policy": { "total": 288.7080791220004, "count": 90, "is_parallel": true, "self": 102.54170750700115, "children": { "TorchPPOOptimizer.update": { "total": 186.16637161499926, "count": 4587, "is_parallel": true, "self": 186.16637161499926 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1704317499999206, "count": 1, "self": 0.001631586999906176, "children": { "RLTrainer._checkpoint": { "total": 0.16880016300001444, "count": 1, "self": 0.16880016300001444 } } } } } } }