{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9888315200805664, "min": 0.9888315200805664, "max": 2.855564594268799, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9452.240234375, "min": 9452.240234375, "max": 29243.8359375, "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": 12.816967010498047, "min": 0.23591682314872742, "max": 12.816967010498047, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2499.30859375, "min": 45.76786422729492, "max": 2610.28564453125, "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.Losses.PolicyLoss.mean": { "value": 0.04391905067313928, "min": 0.03950252620916217, "max": 0.05311287571885259, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.17567620269255713, "min": 0.17064426634897245, "max": 0.24235226161181345, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2701241783797741, "min": 0.12800076749408618, "max": 0.3960992503911257, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.0804967135190964, "min": 0.5120030699763447, "max": 1.9804962519556284, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.00029188200270599996, "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": 0.00014443060000000012, "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.CumulativeReward.mean": { "value": 25.363636363636363, "min": 2.5681818181818183, "max": 25.477272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1116.0, "min": 113.0, "max": 1397.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.363636363636363, "min": 2.5681818181818183, "max": 25.477272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1116.0, "min": 113.0, "max": 1397.0, "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": "1685073633", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1685074147" }, "total": 514.1420796299999, "count": 1, "self": 0.43084550499975194, "children": { "run_training.setup": { "total": 0.044258694000006926, "count": 1, "self": 0.044258694000006926 }, "TrainerController.start_learning": { "total": 513.6669754310001, "count": 1, "self": 0.562318051011971, "children": { "TrainerController._reset_env": { "total": 4.3605247469999995, "count": 1, "self": 4.3605247469999995 }, "TrainerController.advance": { "total": 508.586605673988, "count": 18201, "self": 0.3134256319848987, "children": { "env_step": { "total": 508.2731800420031, "count": 18201, "self": 356.1300800500144, "children": { "SubprocessEnvManager._take_step": { "total": 151.85633005299331, "count": 18201, "self": 2.0580368299964107, "children": { "TorchPolicy.evaluate": { "total": 149.7982932229969, "count": 18201, "self": 149.7982932229969 } } }, "workers": { "total": 0.2867699389954055, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 511.9404297619963, "count": 18201, "is_parallel": true, "self": 245.47475391198657, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00562625999998545, "count": 1, "is_parallel": true, "self": 0.003856539000025805, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017697209999596453, "count": 10, "is_parallel": true, "self": 0.0017697209999596453 } } }, "UnityEnvironment.step": { "total": 0.11647435600002609, "count": 1, "is_parallel": true, "self": 0.0006805440000334784, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00049897299999202, "count": 1, "is_parallel": true, "self": 0.00049897299999202 }, "communicator.exchange": { "total": 0.1131877590000272, "count": 1, "is_parallel": true, "self": 0.1131877590000272 }, "steps_from_proto": { "total": 0.0021070799999733936, "count": 1, "is_parallel": true, "self": 0.0003933499999675405, "children": { "_process_rank_one_or_two_observation": { "total": 0.001713730000005853, "count": 10, "is_parallel": true, "self": 0.001713730000005853 } } } } } } }, "UnityEnvironment.step": { "total": 266.46567585000975, "count": 18200, "is_parallel": true, "self": 10.583097644011787, "children": { "UnityEnvironment._generate_step_input": { "total": 5.940315582999688, "count": 18200, "is_parallel": true, "self": 5.940315582999688 }, "communicator.exchange": { "total": 211.8124055899945, "count": 18200, "is_parallel": true, "self": 211.8124055899945 }, "steps_from_proto": { "total": 38.12985703300376, "count": 18200, "is_parallel": true, "self": 7.522578980974004, "children": { "_process_rank_one_or_two_observation": { "total": 30.607278052029756, "count": 182000, "is_parallel": true, "self": 30.607278052029756 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013308800009781407, "count": 1, "self": 0.00013308800009781407, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 504.39721214206645, "count": 475316, "is_parallel": true, "self": 11.455201589067315, "children": { "process_trajectory": { "total": 274.463578025999, "count": 475316, "is_parallel": true, "self": 272.396942303999, "children": { "RLTrainer._checkpoint": { "total": 2.066635722000001, "count": 4, "is_parallel": true, "self": 2.066635722000001 } } }, "_update_policy": { "total": 218.4784325270001, "count": 90, "is_parallel": true, "self": 109.32704281100047, "children": { "TorchPPOOptimizer.update": { "total": 109.15138971599964, "count": 2880, "is_parallel": true, "self": 109.15138971599964 } } } } } } } } }, "TrainerController._save_models": { "total": 0.15739387099995383, "count": 1, "self": 0.0008773449999353033, "children": { "RLTrainer._checkpoint": { "total": 0.15651652600001853, "count": 1, "self": 0.15651652600001853 } } } } } } }