{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.960408627986908, "min": 0.960408627986908, "max": 2.8603765964508057, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9169.9814453125, "min": 9169.9814453125, "max": 29293.1171875, "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": 13.185778617858887, "min": 0.36993852257728577, "max": 13.185778617858887, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2571.226806640625, "min": 71.76807403564453, "max": 2683.9609375, "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": 0.06744591830553391, "min": 0.06423402978389811, "max": 0.07285882713108816, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26978367322213564, "min": 0.25693611913559244, "max": 0.3632341645949055, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1981726858545752, "min": 0.11776316824013039, "max": 0.27831685178420124, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7926907434183008, "min": 0.47105267296052156, "max": 1.3915842589210061, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000009e-06, "min": 8.082097306000009e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.2328389224000035e-05, "min": 3.2328389224000035e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269399999999998, "min": 0.10269399999999998, "max": 0.197294, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.4107759999999999, "min": 0.4107759999999999, "max": 0.9617200000000001, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.004864970599999999, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.022727272727273, "min": 3.3636363636363638, "max": 26.022727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1145.0, "min": 148.0, "max": 1428.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.022727272727273, "min": 3.3636363636363638, "max": 26.022727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1145.0, "min": 148.0, "max": 1428.0, "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": "1681626737", "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": "1681627244" }, "total": 506.280685182, "count": 1, "self": 0.3838842229999955, "children": { "run_training.setup": { "total": 0.11859015700002828, "count": 1, "self": 0.11859015700002828 }, "TrainerController.start_learning": { "total": 505.778210802, "count": 1, "self": 0.5083178599988969, "children": { "TrainerController._reset_env": { "total": 4.839040935000014, "count": 1, "self": 4.839040935000014 }, "TrainerController.advance": { "total": 500.299162148001, "count": 18202, "self": 0.25573683899511934, "children": { "env_step": { "total": 500.0434253090059, "count": 18202, "self": 380.61443995700506, "children": { "SubprocessEnvManager._take_step": { "total": 119.17854226999293, "count": 18202, "self": 1.6043095009932244, "children": { "TorchPolicy.evaluate": { "total": 117.5742327689997, "count": 18202, "self": 117.5742327689997 } } }, "workers": { "total": 0.2504430820079051, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 504.4472105660032, "count": 18202, "is_parallel": true, "self": 266.254057028008, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005070897999985391, "count": 1, "is_parallel": true, "self": 0.003721625000025597, "children": { "_process_rank_one_or_two_observation": { "total": 0.001349272999959794, "count": 10, "is_parallel": true, "self": 0.001349272999959794 } } }, "UnityEnvironment.step": { "total": 0.053903386000001774, "count": 1, "is_parallel": true, "self": 0.0005528150000486676, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004075939999665934, "count": 1, "is_parallel": true, "self": 0.0004075939999665934 }, "communicator.exchange": { "total": 0.04568270200002189, "count": 1, "is_parallel": true, "self": 0.04568270200002189 }, "steps_from_proto": { "total": 0.007260274999964622, "count": 1, "is_parallel": true, "self": 0.0004108759999326139, "children": { "_process_rank_one_or_two_observation": { "total": 0.006849399000032008, "count": 10, "is_parallel": true, "self": 0.006849399000032008 } } } } } } }, "UnityEnvironment.step": { "total": 238.19315353799522, "count": 18201, "is_parallel": true, "self": 9.542025044999718, "children": { "UnityEnvironment._generate_step_input": { "total": 5.342199058995448, "count": 18201, "is_parallel": true, "self": 5.342199058995448 }, "communicator.exchange": { "total": 192.45464624900495, "count": 18201, "is_parallel": true, "self": 192.45464624900495 }, "steps_from_proto": { "total": 30.854283184995097, "count": 18201, "is_parallel": true, "self": 6.01669032700147, "children": { "_process_rank_one_or_two_observation": { "total": 24.837592857993627, "count": 182010, "is_parallel": true, "self": 24.837592857993627 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00010619099998621095, "count": 1, "self": 0.00010619099998621095, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 496.7644013499382, "count": 389224, "is_parallel": true, "self": 9.723601140964888, "children": { "process_trajectory": { "total": 241.968096317973, "count": 389224, "is_parallel": true, "self": 240.951042819973, "children": { "RLTrainer._checkpoint": { "total": 1.0170534979999957, "count": 4, "is_parallel": true, "self": 1.0170534979999957 } } }, "_update_policy": { "total": 245.07270389100034, "count": 90, "is_parallel": true, "self": 97.64208174900023, "children": { "TorchPPOOptimizer.update": { "total": 147.43062214200012, "count": 7645, "is_parallel": true, "self": 147.43062214200012 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1315836680000757, "count": 1, "self": 0.000853305000077853, "children": { "RLTrainer._checkpoint": { "total": 0.13073036299999785, "count": 1, "self": 0.13073036299999785 } } } } } } }