{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.1999590396881104, "min": 3.1999006271362305, "max": 3.241605281829834, "count": 37 }, "SoccerTwos.Policy.Entropy.sum": { "value": 66866.34375, "min": 29757.73046875, "max": 103708.4140625, "count": 37 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 980.2, "min": 354.26666666666665, "max": 999.0, "count": 37 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19604.0, "min": 8220.0, "max": 28456.0, "count": 37 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1211.9378862333965, "min": 1205.1835371958437, "max": 1215.6735285543373, "count": 35 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2423.875772466793, "min": 2412.7680449870254, "max": 26723.470354880505, "count": 35 }, "SoccerTwos.Step.mean": { "value": 699154.0, "min": 339906.0, "max": 699154.0, "count": 37 }, "SoccerTwos.Step.sum": { "value": 699154.0, "min": 339906.0, "max": 699154.0, "count": 37 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.004377217032015324, "min": -0.011403935961425304, "max": 0.00670193787664175, "count": 37 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.043772172182798386, "min": -0.21572968363761902, "max": 0.09587319940328598, "count": 37 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0028003088664263487, "min": -0.013163342140614986, "max": 0.006617785431444645, "count": 37 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.028003089129924774, "min": -0.23477448523044586, "max": 0.09730030596256256, "count": 37 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 37 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 37 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.2, "min": -0.5555200020472209, "max": 0.3996470535502714, "count": 37 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -2.0, "min": -9.0, "max": 6.793999910354614, "count": 37 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.2, "min": -0.5555200020472209, "max": 0.3996470535502714, "count": 37 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -2.0, "min": -9.0, "max": 6.793999910354614, "count": 37 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 37 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 37 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.0159091107120427, "min": 0.012636019413669904, "max": 0.020098431833321228, "count": 17 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.0159091107120427, "min": 0.012636019413669904, "max": 0.020098431833321228, "count": 17 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.002516983779302488, "min": 0.00014130498408727968, "max": 0.0086365083232522, "count": 17 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.002516983779302488, "min": 0.00014130498408727968, "max": 0.0086365083232522, "count": 17 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.002624650854462137, "min": 0.00014110098109085812, "max": 0.008632027031853794, "count": 17 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.002624650854462137, "min": 0.00014110098109085812, "max": 0.008632027031853794, "count": 17 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 17 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 17 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.25, "min": 0.25, "max": 0.25, "count": 17 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.25, "min": 0.25, "max": 0.25, "count": 17 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.010000000000000002, "min": 0.010000000000000002, "max": 0.010000000000000002, "count": 17 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.010000000000000002, "min": 0.010000000000000002, "max": 0.010000000000000002, "count": 17 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1683407536", "python_version": "3.9.16 | packaged by conda-forge | (main, Feb 1 2023, 21:38:11) \n[Clang 14.0.6 ]", "command_line_arguments": "/Users/andreas.bjarlestam/mambaforge/envs/huggingface-rl-course/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --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": "1.11.0", "numpy_version": "1.21.2", "end_time_seconds": "1683409217" }, "total": 1680.865004125, "count": 1, "self": 0.12260970800002724, "children": { "run_training.setup": { "total": 0.013448125000000033, "count": 1, "self": 0.013448125000000033 }, "TrainerController.start_learning": { "total": 1680.728946292, "count": 1, "self": 0.2918064929965567, "children": { "TrainerController._reset_env": { "total": 1.733552874999984, "count": 3, "self": 1.733552874999984 }, "TrainerController.advance": { "total": 1678.5335023400037, "count": 24247, "self": 0.28358365201415836, "children": { "env_step": { "total": 1387.8335258989998, "count": 24247, "self": 1339.7047586980023, "children": { "SubprocessEnvManager._take_step": { "total": 47.923312614988625, "count": 24247, "self": 1.4153185770023171, "children": { "TorchPolicy.evaluate": { "total": 46.50799403798631, "count": 48068, "self": 46.50799403798631 } } }, "workers": { "total": 0.20545458600886946, "count": 24246, "self": 0.0, "children": { "worker_root": { "total": 1678.4846704740066, "count": 24246, "is_parallel": true, "self": 380.76107760500213, "children": { "steps_from_proto": { "total": 0.005257666000014982, "count": 6, "is_parallel": true, "self": 0.0006387100000131429, "children": { "_process_rank_one_or_two_observation": { "total": 0.004618956000001839, "count": 24, "is_parallel": true, "self": 0.004618956000001839 } } }, "UnityEnvironment.step": { "total": 1297.7183352030045, "count": 24246, "is_parallel": true, "self": 3.2725019259994497, "children": { "UnityEnvironment._generate_step_input": { "total": 22.31964003499131, "count": 24246, "is_parallel": true, "self": 22.31964003499131 }, "communicator.exchange": { "total": 1224.7218267430092, "count": 24246, "is_parallel": true, "self": 1224.7218267430092 }, "steps_from_proto": { "total": 47.40436649900448, "count": 48492, "is_parallel": true, "self": 5.1485635459650325, "children": { "_process_rank_one_or_two_observation": { "total": 42.25580295303945, "count": 193968, "is_parallel": true, "self": 42.25580295303945 } } } } } } } } } } }, "trainer_advance": { "total": 290.41639278898964, "count": 24246, "self": 2.2689823499720774, "children": { "process_trajectory": { "total": 40.91866668901776, "count": 24246, "self": 40.91866668901776 }, "_update_policy": { "total": 247.2287437499998, "count": 17, "self": 32.059548280997035, "children": { "TorchPOCAOptimizer.update": { "total": 215.16919546900277, "count": 510, "self": 215.16919546900277 } } } } } } }, "trainer_threads": { "total": 5.839999630552484e-07, "count": 1, "self": 5.839999630552484e-07 }, "TrainerController._save_models": { "total": 0.17008399999986068, "count": 1, "self": 0.001209707999805687, "children": { "RLTrainer._checkpoint": { "total": 0.168874292000055, "count": 1, "self": 0.168874292000055 } } } } } } }