{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.7670687437057495, "min": 1.762378215789795, "max": 1.7670687437057495, "count": 2 }, "SoccerTwos.Policy.Entropy.sum": { "value": 35680.65234375, "min": 20584.578125, "max": 35680.65234375, "count": 2 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 45.157407407407405, "min": 43.37931034482759, "max": 45.157407407407405, "count": 2 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19508.0, "min": 10064.0, "max": 19508.0, "count": 2 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1516.1834039857301, "min": 1516.1834039857301, "max": 1524.068960336238, "count": 2 }, "SoccerTwos.Self-play.ELO.sum": { "value": 327495.6152609177, "min": 176791.9993990036, "max": 327495.6152609177, "count": 2 }, "SoccerTwos.Step.mean": { "value": 6369930.0, "min": 6359986.0, "max": 6369930.0, "count": 2 }, "SoccerTwos.Step.sum": { "value": 6369930.0, "min": 6359986.0, "max": 6369930.0, "count": 2 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.021821845322847366, "min": -0.033418405801057816, "max": 0.021821845322847366, "count": 2 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 4.735340595245361, "min": -3.8096981048583984, "max": 4.735340595245361, "count": 2 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.024178503081202507, "min": -0.03187581151723862, "max": 0.024178503081202507, "count": 2 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 5.246735095977783, "min": -3.6338424682617188, "max": 5.246735095977783, "count": 2 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.09724977049410069, "min": -0.1783824542112518, "max": -0.09724977049410069, "count": 2 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -21.10320019721985, "min": -21.10320019721985, "max": -20.335599780082703, "count": 2 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.09724977049410069, "min": -0.1783824542112518, "max": -0.09724977049410069, "count": 2 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -21.10320019721985, "min": -21.10320019721985, "max": -20.335599780082703, "count": 2 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1676698817", "python_version": "3.9.16 (main, Jan 11 2023, 16:16:36) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\ProgramData\\Anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.13.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1676699297" }, "total": 479.93567010000004, "count": 1, "self": 0.11912370000004557, "children": { "run_training.setup": { "total": 0.1977764999999998, "count": 1, "self": 0.1977764999999998 }, "TrainerController.start_learning": { "total": 479.6187699, "count": 1, "self": 0.0598777999991853, "children": { "TrainerController._reset_env": { "total": 5.679755699999999, "count": 2, "self": 5.679755699999999 }, "TrainerController.advance": { "total": 473.3129289000008, "count": 1523, "self": 0.05820720000019719, "children": { "env_step": { "total": 368.3146211000004, "count": 1523, "self": 356.8989969999999, "children": { "SubprocessEnvManager._take_step": { "total": 11.381359400000026, "count": 1523, "self": 0.3395957999998771, "children": { "TorchPolicy.evaluate": { "total": 11.041763600000149, "count": 2666, "self": 11.041763600000149 } } }, "workers": { "total": 0.03426470000047921, "count": 1522, "self": 0.0, "children": { "worker_root": { "total": 473.7135603999999, "count": 1522, "is_parallel": true, "self": 123.88864579999921, "children": { "steps_from_proto": { "total": 0.012227299999999275, "count": 4, "is_parallel": true, "self": 0.001752699999998164, "children": { "_process_rank_one_or_two_observation": { "total": 0.01047460000000111, "count": 16, "is_parallel": true, "self": 0.01047460000000111 } } }, "UnityEnvironment.step": { "total": 349.8126873000007, "count": 1522, "is_parallel": true, "self": 0.6091552000004867, "children": { "UnityEnvironment._generate_step_input": { "total": 8.091192600000177, "count": 1522, "is_parallel": true, "self": 8.091192600000177 }, "communicator.exchange": { "total": 331.14293009999983, "count": 1522, "is_parallel": true, "self": 331.14293009999983 }, "steps_from_proto": { "total": 9.969409400000174, "count": 3044, "is_parallel": true, "self": 1.3470471999977551, "children": { "_process_rank_one_or_two_observation": { "total": 8.622362200002419, "count": 12176, "is_parallel": true, "self": 8.622362200002419 } } } } } } } } } } }, "trainer_advance": { "total": 104.9401006000002, "count": 1522, "self": 0.4407020000000159, "children": { "process_trajectory": { "total": 17.492944100000173, "count": 1522, "self": 17.492944100000173 }, "_update_policy": { "total": 87.00645450000002, "count": 1, "self": 8.153334699999903, "children": { "TorchPOCAOptimizer.update": { "total": 78.85311980000012, "count": 30, "self": 78.85311980000012 } } } } } } }, "trainer_threads": { "total": 2.300000005561742e-06, "count": 1, "self": 2.300000005561742e-06 }, "TrainerController._save_models": { "total": 0.5662052000000131, "count": 1, "self": 0.004798500000049444, "children": { "RLTrainer._checkpoint": { "total": 0.5614066999999636, "count": 1, "self": 0.5614066999999636 } } } } } } }