{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.7201579809188843, "min": 1.123506784439087, "max": 3.2957563400268555, "count": 2257 }, "SoccerTwos.Policy.Entropy.sum": { "value": 35669.1953125, "min": 11119.375, "max": 127170.734375, "count": 2257 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 59.83132530120482, "min": 44.706422018348626, "max": 999.0, "count": 2257 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19864.0, "min": 3996.0, "max": 30420.0, "count": 2257 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1607.4298139690143, "min": 1200.059470768892, "max": 1612.0985701274526, "count": 1386 }, "SoccerTwos.Self-play.ELO.sum": { "value": 266833.34911885636, "min": 2401.4985608882907, "max": 343303.541986933, "count": 1386 }, "SoccerTwos.Step.mean": { "value": 22569991.0, "min": 9226.0, "max": 22569991.0, "count": 2257 }, "SoccerTwos.Step.sum": { "value": 22569991.0, "min": 9226.0, "max": 22569991.0, "count": 2257 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0014907373115420341, "min": -0.1771720051765442, "max": 0.162044495344162, "count": 2257 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.24746239185333252, "min": -24.804080963134766, "max": 25.267377853393555, "count": 2257 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0026493940968066454, "min": -0.1726289987564087, "max": 0.1582309752702713, "count": 2257 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.439799427986145, "min": -24.168060302734375, "max": 25.120586395263672, "count": 2257 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2257 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2257 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.05299759054758463, "min": -0.6828941176919376, "max": 0.39180392319080876, "count": 2257 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 8.797600030899048, "min": -68.89759993553162, "max": 46.495199501514435, "count": 2257 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.05299759054758463, "min": -0.6828941176919376, "max": 0.39180392319080876, "count": 2257 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 8.797600030899048, "min": -68.89759993553162, "max": 46.495199501514435, "count": 2257 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2257 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2257 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017498067223156492, "min": 0.00948568816917638, "max": 0.026053908591469128, "count": 1061 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017498067223156492, "min": 0.00948568816917638, "max": 0.026053908591469128, "count": 1061 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09208467875917753, "min": 1.1610315819865492e-09, "max": 0.11759451304872831, "count": 1061 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09208467875917753, "min": 1.1610315819865492e-09, "max": 0.11759451304872831, "count": 1061 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09341064294179281, "min": 2.00973796493642e-09, "max": 0.12018106505274773, "count": 1061 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09341064294179281, "min": 2.00973796493642e-09, "max": 0.12018106505274773, "count": 1061 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1061 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1061 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 1061 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 1061 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 1061 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 1061 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1716987412", "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\goenuer\\AppData\\Local\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1717069845" }, "total": 82431.191737, "count": 1, "self": 0.3341365000087535, "children": { "run_training.setup": { "total": 0.051550700000007055, "count": 1, "self": 0.051550700000007055 }, "TrainerController.start_learning": { "total": 82430.8060498, "count": 1, "self": 42.6294809961837, "children": { "TrainerController._reset_env": { "total": 11.149112099968988, "count": 113, "self": 11.149112099968988 }, "TrainerController.advance": { "total": 82376.92790780385, "count": 1500448, "self": 39.397979398374446, "children": { "env_step": { "total": 31537.608235002797, "count": 1500448, "self": 22916.522104093245, "children": { "SubprocessEnvManager._take_step": { "total": 8592.994472102546, "count": 1500448, "self": 242.09125830226367, "children": { "TorchPolicy.evaluate": { "total": 8350.903213800282, "count": 2884426, "self": 8350.903213800282 } } }, "workers": { "total": 28.091658807005842, "count": 1500448, "self": 0.0, "children": { "worker_root": { "total": 82339.06907509743, "count": 1500448, "is_parallel": true, "self": 64443.2750590925, "children": { "steps_from_proto": { "total": 0.2198060000218902, "count": 226, "is_parallel": true, "self": 0.047515099827251106, "children": { "_process_rank_one_or_two_observation": { "total": 0.1722909001946391, "count": 904, "is_parallel": true, "self": 0.1722909001946391 } } }, "UnityEnvironment.step": { "total": 17895.57421000491, "count": 1500448, "is_parallel": true, "self": 921.8253366180979, "children": { "UnityEnvironment._generate_step_input": { "total": 1046.900928999402, "count": 1500448, "is_parallel": true, "self": 1046.900928999402 }, "communicator.exchange": { "total": 12743.237707100077, "count": 1500448, "is_parallel": true, "self": 12743.237707100077 }, "steps_from_proto": { "total": 3183.610237287333, "count": 3000896, "is_parallel": true, "self": 701.5935264930386, "children": { "_process_rank_one_or_two_observation": { "total": 2482.0167107942943, "count": 12003584, "is_parallel": true, "self": 2482.0167107942943 } } } } } } } } } } }, "trainer_advance": { "total": 50799.92169340268, "count": 1500448, "self": 331.03031910066056, "children": { "process_trajectory": { "total": 6562.828255102076, "count": 1500448, "self": 6557.342811102043, "children": { "RLTrainer._checkpoint": { "total": 5.485444000032658, "count": 45, "self": 5.485444000032658 } } }, "_update_policy": { "total": 43906.06311919994, "count": 1062, "self": 2473.433702100643, "children": { "TorchPOCAOptimizer.update": { "total": 41432.6294170993, "count": 31868, "self": 41432.6294170993 } } } } } } }, "trainer_threads": { "total": 8.999923011288047e-07, "count": 1, "self": 8.999923011288047e-07 }, "TrainerController._save_models": { "total": 0.09954799999832176, "count": 1, "self": 0.001979099994059652, "children": { "RLTrainer._checkpoint": { "total": 0.0975689000042621, "count": 1, "self": 0.0975689000042621 } } } } } } }