{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8137714862823486, "min": 0.8137714862823486, "max": 2.869044303894043, "count": 25 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7707.2294921875, "min": 7707.2294921875, "max": 29413.44140625, "count": 25 }, "SnowballTarget.Step.mean": { "value": 249944.0, "min": 9952.0, "max": 249944.0, "count": 25 }, "SnowballTarget.Step.sum": { "value": 249944.0, "min": 9952.0, "max": 249944.0, "count": 25 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.057310104370117, "min": 0.489102303981781, "max": 13.057310104370117, "count": 25 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2533.1181640625, "min": 94.88584899902344, "max": 2652.577880859375, "count": 25 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 25 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 25 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.045327773664212145, "min": 0.040881592306686795, "max": 0.056708568940545476, "count": 25 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.18131109465684858, "min": 0.16974761146896827, "max": 0.2791657846513166, "count": 25 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.23267300721878809, "min": 0.1377695006473611, "max": 0.3097350304325422, "count": 25 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9306920288751523, "min": 0.5510780025894444, "max": 1.548675152162711, "count": 25 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 5.745698084800001e-06, "min": 5.745698084800001e-06, "max": 0.0002935056021648, "count": 25 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 2.2982792339200003e-05, "min": 2.2982792339200003e-05, "max": 0.0014081280306239999, "count": 25 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10191520000000001, "min": 0.10191520000000001, "max": 0.19783520000000002, "count": 25 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.40766080000000005, "min": 0.40766080000000005, "max": 0.9693760000000001, "count": 25 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00010556848000000001, "min": 0.00010556848000000001, "max": 0.00489197648, "count": 25 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00042227392000000004, "min": 0.00042227392000000004, "max": 0.0234718624, "count": 25 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.84090909090909, "min": 4.0, "max": 25.84090909090909, "count": 25 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1137.0, "min": 176.0, "max": 1410.0, "count": 25 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.84090909090909, "min": 4.0, "max": 25.84090909090909, "count": 25 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1137.0, "min": 176.0, "max": 1410.0, "count": 25 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 25 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 25 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679206781", "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": "1679207362" }, "total": 580.2368511, "count": 1, "self": 0.43813578599997527, "children": { "run_training.setup": { "total": 0.11715918800001646, "count": 1, "self": 0.11715918800001646 }, "TrainerController.start_learning": { "total": 579.681556126, "count": 1, "self": 0.7008679089988163, "children": { "TrainerController._reset_env": { "total": 9.225281198999994, "count": 1, "self": 9.225281198999994 }, "TrainerController.advance": { "total": 569.6020354370012, "count": 22737, "self": 0.37673386701044365, "children": { "env_step": { "total": 569.2253015699907, "count": 22737, "self": 393.782854903991, "children": { "SubprocessEnvManager._take_step": { "total": 175.08981056699366, "count": 22737, "self": 2.9247177799998667, "children": { "TorchPolicy.evaluate": { "total": 172.1650927869938, "count": 22737, "self": 172.1650927869938 } } }, "workers": { "total": 0.3526360990060766, "count": 22737, "self": 0.0, "children": { "worker_root": { "total": 577.7399792669971, "count": 22737, "is_parallel": true, "self": 264.4437365459913, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005391672999962793, "count": 1, "is_parallel": true, "self": 0.0037846860000172455, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016069869999455477, "count": 10, "is_parallel": true, "self": 0.0016069869999455477 } } }, "UnityEnvironment.step": { "total": 0.08483345999997027, "count": 1, "is_parallel": true, "self": 0.000652628999944227, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041791199998897355, "count": 1, "is_parallel": true, "self": 0.00041791199998897355 }, "communicator.exchange": { "total": 0.08158782500004236, "count": 1, "is_parallel": true, "self": 0.08158782500004236 }, "steps_from_proto": { "total": 0.002175093999994715, "count": 1, "is_parallel": true, "self": 0.00044242600000643506, "children": { "_process_rank_one_or_two_observation": { "total": 0.00173266799998828, "count": 10, "is_parallel": true, "self": 0.00173266799998828 } } } } } } }, "UnityEnvironment.step": { "total": 313.2962427210058, "count": 22736, "is_parallel": true, "self": 12.466406117023496, "children": { "UnityEnvironment._generate_step_input": { "total": 6.949217403991042, "count": 22736, "is_parallel": true, "self": 6.949217403991042 }, "communicator.exchange": { "total": 251.94485081299882, "count": 22736, "is_parallel": true, "self": 251.94485081299882 }, "steps_from_proto": { "total": 41.935768386992436, "count": 22736, "is_parallel": true, "self": 8.444905304998144, "children": { "_process_rank_one_or_two_observation": { "total": 33.49086308199429, "count": 227360, "is_parallel": true, "self": 33.49086308199429 } } } } } } } } } } } } }, "trainer_threads": { "total": 3.657500008102943e-05, "count": 1, "self": 3.657500008102943e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 564.7934233820006, "count": 528629, "is_parallel": true, "self": 13.520736042981298, "children": { "process_trajectory": { "total": 336.6830797370197, "count": 528629, "is_parallel": true, "self": 334.8585658720196, "children": { "RLTrainer._checkpoint": { "total": 1.8245138650000854, "count": 5, "is_parallel": true, "self": 1.8245138650000854 } } }, "_update_policy": { "total": 214.5896076019996, "count": 113, "is_parallel": true, "self": 96.5695248330012, "children": { "TorchPPOOptimizer.update": { "total": 118.0200827689984, "count": 2712, "is_parallel": true, "self": 118.0200827689984 } } } } } } } } }, "TrainerController._save_models": { "total": 0.15333500600002026, "count": 1, "self": 0.0008617930000127672, "children": { "RLTrainer._checkpoint": { "total": 0.1524732130000075, "count": 1, "self": 0.1524732130000075 } } } } } } }