{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.4567415714263916, "min": 1.3126190900802612, "max": 3.2957043647766113, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 28761.90625, "min": 20743.95703125, "max": 132507.15625, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 52.351063829787236, "min": 39.52, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19684.0, "min": 7992.0, "max": 27920.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1649.5823315696862, "min": 1196.6379404980053, "max": 1746.240399168466, "count": 4969 }, "SoccerTwos.Self-play.ELO.sum": { "value": 310121.478335101, "min": 2393.2758809960105, "max": 410382.6908686255, "count": 4969 }, "SoccerTwos.Step.mean": { "value": 49999914.0, "min": 9550.0, "max": 49999914.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999914.0, "min": 9550.0, "max": 49999914.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.07750029116868973, "min": -0.13002663850784302, "max": 0.20040389895439148, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -14.57005500793457, "min": -23.36751937866211, "max": 31.813045501708984, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.07770086079835892, "min": -0.13141168653964996, "max": 0.19435946643352509, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -14.607762336730957, "min": -22.205169677734375, "max": 31.409889221191406, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.15238297809945775, "min": -0.7142857142857143, "max": 0.48140241367271147, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -28.64799988269806, "min": -67.65360009670258, "max": 63.22719943523407, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.15238297809945775, "min": -0.7142857142857143, "max": 0.48140241367271147, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -28.64799988269806, "min": -67.65360009670258, "max": 63.22719943523407, "count": 5000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017055213035200724, "min": 0.009752229471147681, "max": 0.025547918040926258, "count": 2423 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017055213035200724, "min": 0.009752229471147681, "max": 0.025547918040926258, "count": 2423 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10096047694484393, "min": 7.215567302409909e-06, "max": 0.1292221556107203, "count": 2423 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10096047694484393, "min": 7.215567302409909e-06, "max": 0.1292221556107203, "count": 2423 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10134102652470271, "min": 7.898130525063607e-06, "max": 0.1324529307583968, "count": 2423 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10134102652470271, "min": 7.898130525063607e-06, "max": 0.1324529307583968, "count": 2423 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2423 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2423 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 2423 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 2423 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2423 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2423 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675329634", "python_version": "3.8.16 | packaged by conda-forge | (default, Feb 1 2023, 16:01:55) \n[GCC 11.3.0]", "command_line_arguments": "/opt/conda/envs/rl/bin/mlagents-learn config/poca/SoccerTwos.yaml --env ../env/SoccerTows.x86_64 --run-id nachshonc_v1 --no-graphics --force", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1675437122" }, "total": 107488.28744331401, "count": 1, "self": 0.3362978690129239, "children": { "run_training.setup": { "total": 0.01918340900000004, "count": 1, "self": 0.01918340900000004 }, "TrainerController.start_learning": { "total": 107487.931962036, "count": 1, "self": 83.91960325575201, "children": { "TrainerController._reset_env": { "total": 13.701780004989097, "count": 250, "self": 13.701780004989097 }, "TrainerController.advance": { "total": 107389.73796373328, "count": 3441322, "self": 89.4884539435734, "children": { "env_step": { "total": 80250.48119759267, "count": 3441322, "self": 58430.20581952722, "children": { "SubprocessEnvManager._take_step": { "total": 21768.999314276625, "count": 3441322, "self": 515.6430356909405, "children": { "TorchPolicy.evaluate": { "total": 21253.356278585685, "count": 6282110, "self": 21253.356278585685 } } }, "workers": { "total": 51.27606378882807, "count": 3441322, "self": 0.0, "children": { "worker_root": { "total": 107318.01145466334, "count": 3441322, "is_parallel": true, "self": 58591.8244719033, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004790505000002554, "count": 2, "is_parallel": true, "self": 0.002787836000010202, "children": { "_process_rank_one_or_two_observation": { "total": 0.002002668999992352, "count": 8, "is_parallel": true, "self": 0.002002668999992352 } } }, "UnityEnvironment.step": { "total": 0.07278313799999836, "count": 1, "is_parallel": true, "self": 0.0006551979999969149, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004804220000025339, "count": 1, "is_parallel": true, "self": 0.0004804220000025339 }, "communicator.exchange": { "total": 0.023657260999996765, "count": 1, "is_parallel": true, "self": 0.023657260999996765 }, "steps_from_proto": { "total": 0.047990257000002146, "count": 2, "is_parallel": true, "self": 0.0004740980000050854, "children": { "_process_rank_one_or_two_observation": { "total": 0.04751615899999706, "count": 8, "is_parallel": true, "self": 0.04751615899999706 } } } } } } }, "UnityEnvironment.step": { "total": 48725.62705070806, "count": 3441321, "is_parallel": true, "self": 2561.9700887540166, "children": { "UnityEnvironment._generate_step_input": { "total": 1686.7395188800815, "count": 3441321, "is_parallel": true, "self": 1686.7395188800815 }, "communicator.exchange": { "total": 36563.25568634441, "count": 3441321, "is_parallel": true, "self": 36563.25568634441 }, "steps_from_proto": { "total": 7913.661756729556, "count": 6882642, "is_parallel": true, "self": 1541.4449322352084, "children": { "_process_rank_one_or_two_observation": { "total": 6372.216824494348, "count": 27530568, "is_parallel": true, "self": 6372.216824494348 } } } } }, "steps_from_proto": { "total": 0.5599320519748403, "count": 498, "is_parallel": true, "self": 0.11079636092500778, "children": { "_process_rank_one_or_two_observation": { "total": 0.44913569104983253, "count": 1992, "is_parallel": true, "self": 0.44913569104983253 } } } } } } } } }, "trainer_advance": { "total": 27049.768312197037, "count": 3441322, "self": 609.4411538380627, "children": { "process_trajectory": { "total": 12460.254691461007, "count": 3441322, "self": 12410.249031787978, "children": { "RLTrainer._checkpoint": { "total": 50.00565967302839, "count": 100, "self": 50.00565967302839 } } }, "_update_policy": { "total": 13980.072466897966, "count": 2423, "self": 8165.400367447144, "children": { "TorchPOCAOptimizer.update": { "total": 5814.672099450821, "count": 72699, "self": 5814.672099450821 } } } } } } }, "trainer_threads": { "total": 8.279894245788455e-07, "count": 1, "self": 8.279894245788455e-07 }, "TrainerController._save_models": { "total": 0.572614213990164, "count": 1, "self": 0.04405526698974427, "children": { "RLTrainer._checkpoint": { "total": 0.5285589470004197, "count": 1, "self": 0.5285589470004197 } } } } } } }