{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": -3.576278402306343e-07, "min": -3.576278402306343e-07, "max": 2.557163715362549, "count": 1132 }, "SoccerTwos.Policy.Entropy.sum": { "value": -0.00946426298469305, "min": -0.01506040245294571, "max": 76979.546875, "count": 1132 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 999.0, "min": 292.7857142857143, "max": 999.0, "count": 1132 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19980.0, "min": 3996.0, "max": 30500.0, "count": 1132 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1217.9983411658543, "min": 1195.3378159121753, "max": 1226.1962097703772, "count": 930 }, "SoccerTwos.Self-play.ELO.sum": { "value": 7307.990046995126, "min": 2392.145426596695, "max": 31557.451750627508, "count": 930 }, "SoccerTwos.Step.mean": { "value": 11319452.0, "min": 9268.0, "max": 11319452.0, "count": 1132 }, "SoccerTwos.Step.sum": { "value": 11319452.0, "min": 9268.0, "max": 11319452.0, "count": 1132 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.661151111125946, "min": -18.157546997070312, "max": 35.32452392578125, "count": 1132 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 6.61151123046875, "min": -363.15093994140625, "max": 751.2879028320312, "count": 1132 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6578042507171631, "min": -17.91787338256836, "max": 34.58213424682617, "count": 1132 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 6.578042507171631, "min": -358.35748291015625, "max": 725.6465454101562, "count": 1132 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1132 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1132 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0, "min": -0.625, "max": 0.48564211318367406, "count": 1132 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.0, "min": -12.221199989318848, "max": 11.304799914360046, "count": 1132 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0, "min": -0.625, "max": 0.48564211318367406, "count": 1132 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.0, "min": -12.221199989318848, "max": 11.304799914360046, "count": 1132 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1132 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1132 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017271466801563898, "min": 0.01025862561412699, "max": 0.9351533432801564, "count": 524 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017271466801563898, "min": 0.01025862561412699, "max": 0.9351533432801564, "count": 524 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 7.218246236195167, "min": 0.00014766889119831225, "max": 32919.68486836751, "count": 524 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 7.218246236195167, "min": 0.00014766889119831225, "max": 32919.68486836751, "count": 524 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 7.428483950843414, "min": 0.00042878056410700083, "max": 29269.570963541668, "count": 524 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 7.428483950843414, "min": 0.00042878056410700083, "max": 29269.570963541668, "count": 524 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 524 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 524 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 524 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 524 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 524 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 524 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1723569977", "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\\manug\\miniconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=C:\\Users\\manug\\ml-agents\\training-envs-executables\\SoccerTwos\\SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.0+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1723655904" }, "total": 85927.1624728, "count": 1, "self": 2.2682376000011573, "children": { "run_training.setup": { "total": 0.28242929999760236, "count": 1, "self": 0.28242929999760236 }, "TrainerController.start_learning": { "total": 85924.6118059, "count": 1, "self": 26.896228401674307, "children": { "TrainerController._reset_env": { "total": 18.198888300037652, "count": 57, "self": 18.198888300037652 }, "TrainerController.advance": { "total": 85879.32728509829, "count": 740894, "self": 26.599330598357483, "children": { "env_step": { "total": 20169.867521103308, "count": 740894, "self": 14972.973272791907, "children": { "SubprocessEnvManager._take_step": { "total": 5179.164462507302, "count": 740894, "self": 187.56233811143466, "children": { "TorchPolicy.evaluate": { "total": 4991.602124395868, "count": 1469106, "self": 4991.602124395868 } } }, "workers": { "total": 17.729785804098356, "count": 740894, "self": 0.0, "children": { "worker_root": { "total": 85877.44118350167, "count": 740894, "is_parallel": true, "self": 74464.28552350338, "children": { "steps_from_proto": { "total": 0.14002719999916735, "count": 114, "is_parallel": true, "self": 0.02901829989423277, "children": { "_process_rank_one_or_two_observation": { "total": 0.11100890010493458, "count": 456, "is_parallel": true, "self": 0.11100890010493458 } } }, "UnityEnvironment.step": { "total": 11413.015632798284, "count": 740894, "is_parallel": true, "self": 684.2067775828509, "children": { "UnityEnvironment._generate_step_input": { "total": 665.2635215983828, "count": 740894, "is_parallel": true, "self": 665.2635215983828 }, "communicator.exchange": { "total": 7872.388067304546, "count": 740894, "is_parallel": true, "self": 7872.388067304546 }, "steps_from_proto": { "total": 2191.1572663125044, "count": 1481788, "is_parallel": true, "self": 443.9809436022333, "children": { "_process_rank_one_or_two_observation": { "total": 1747.176322710271, "count": 5927152, "is_parallel": true, "self": 1747.176322710271 } } } } } } } } } } }, "trainer_advance": { "total": 65682.86043339662, "count": 740894, "self": 206.60896219848655, "children": { "process_trajectory": { "total": 7706.6352393983, "count": 740894, "self": 7702.999688698292, "children": { "RLTrainer._checkpoint": { "total": 3.635550700008025, "count": 22, "self": 3.635550700008025 } } }, "_update_policy": { "total": 57769.61623179984, "count": 524, "self": 2635.168282599647, "children": { "TorchPOCAOptimizer.update": { "total": 55134.44794920019, "count": 15738, "self": 55134.44794920019 } } } } } } }, "trainer_threads": { "total": 1.7999991541728377e-06, "count": 1, "self": 1.7999991541728377e-06 }, "TrainerController._save_models": { "total": 0.18940229999134317, "count": 1, "self": 0.01145429999451153, "children": { "RLTrainer._checkpoint": { "total": 0.17794799999683164, "count": 1, "self": 0.17794799999683164 } } } } } } }