{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.539985179901123, "min": 2.5243136882781982, "max": 2.6431827545166016, "count": 100 }, "SoccerTwos.Policy.Entropy.sum": { "value": 47792.36328125, "min": 45656.9140625, "max": 58335.140625, "count": 100 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 64.20779220779221, "min": 50.628865979381445, "max": 79.63934426229508, "count": 100 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19776.0, "min": 18236.0, "max": 21324.0, "count": 100 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1560.2760091386954, "min": 1503.733199891337, "max": 1560.2760091386954, "count": 100 }, "SoccerTwos.Self-play.ELO.sum": { "value": 240282.5054073591, "min": 186762.5450226515, "max": 300955.66193785286, "count": 100 }, "SoccerTwos.Step.mean": { "value": 11999962.0, "min": 11009944.0, "max": 11999962.0, "count": 100 }, "SoccerTwos.Step.sum": { "value": 11999962.0, "min": 11009944.0, "max": 11999962.0, "count": 100 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.026348678395152092, "min": -0.09217014163732529, "max": 0.07006553560495377, "count": 100 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 4.031347751617432, "min": -16.03760528564453, "max": 12.05127239227295, "count": 100 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.026338858529925346, "min": -0.09542960673570633, "max": 0.06922638416290283, "count": 100 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 4.029845237731934, "min": -16.604751586914062, "max": 11.906937599182129, "count": 100 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 100 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 100 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.022709803253996606, "min": -0.3288613148849376, "max": 0.2337775006890297, "count": 100 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -3.4745998978614807, "min": -45.05400013923645, "max": 37.40440011024475, "count": 100 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.022709803253996606, "min": -0.3288613148849376, "max": 0.2337775006890297, "count": 100 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -3.4745998978614807, "min": -45.05400013923645, "max": 37.40440011024475, "count": 100 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.006884503689070698, "min": 0.005133178024940814, "max": 0.006884503689070698, "count": 4 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.006884503689070698, "min": 0.005133178024940814, "max": 0.006884503689070698, "count": 4 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10350061133503914, "min": 0.09496364270647367, "max": 0.10350061133503914, "count": 4 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10350061133503914, "min": 0.09496364270647367, "max": 0.10350061133503914, "count": 4 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10408208171526591, "min": 0.09554371982812881, "max": 0.10408208171526591, "count": 4 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10408208171526591, "min": 0.09554371982812881, "max": 0.10408208171526591, "count": 4 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 4 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 4 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 4 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 4 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 4 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 4 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1742310881", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn SoccerTwos.yaml --env=/kaggle/working/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1742312974" }, "total": 2093.1256926720016, "count": 1, "self": 0.3326236159991822, "children": { "run_training.setup": { "total": 0.08434448600019095, "count": 1, "self": 0.08434448600019095 }, "TrainerController.start_learning": { "total": 2092.7087245700022, "count": 1, "self": 1.9284045217209496, "children": { "TrainerController._reset_env": { "total": 2.4247240550030256, "count": 6, "self": 2.4247240550030256 }, "TrainerController.advance": { "total": 2088.152041477282, "count": 68940, "self": 1.881130409117759, "children": { "env_step": { "total": 1595.5346732529433, "count": 68940, "self": 1151.810062366465, "children": { "SubprocessEnvManager._take_step": { "total": 442.6924785862393, "count": 68940, "self": 11.79233952719369, "children": { "TorchPolicy.evaluate": { "total": 430.9001390590456, "count": 125372, "self": 430.9001390590456 } } }, "workers": { "total": 1.0321323002390272, "count": 68940, "self": 0.0, "children": { "worker_root": { "total": 2089.227157803485, "count": 68940, "is_parallel": true, "self": 1137.753525742075, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003786139004660072, "count": 2, "is_parallel": true, "self": 0.0009333220041298773, "children": { "_process_rank_one_or_two_observation": { "total": 0.0028528170005301945, "count": 8, "is_parallel": true, "self": 0.0028528170005301945 } } }, "UnityEnvironment.step": { "total": 0.04616090399940731, "count": 1, "is_parallel": true, "self": 0.001206628996442305, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000795007999840891, "count": 1, "is_parallel": true, "self": 0.000795007999840891 }, "communicator.exchange": { "total": 0.0406940740031132, "count": 1, "is_parallel": true, "self": 0.0406940740031132 }, "steps_from_proto": { "total": 0.0034651930000109132, "count": 2, "is_parallel": true, "self": 0.0005959990085102618, "children": { "_process_rank_one_or_two_observation": { "total": 0.0028691939915006515, "count": 8, "is_parallel": true, "self": 0.0028691939915006515 } } } } } } }, "steps_from_proto": { "total": 0.010143659997993382, "count": 10, "is_parallel": true, "self": 0.002147706996765919, "children": { "_process_rank_one_or_two_observation": { "total": 0.007995953001227463, "count": 40, "is_parallel": true, "self": 0.007995953001227463 } } }, "UnityEnvironment.step": { "total": 951.4634884014122, "count": 68939, "is_parallel": true, "self": 52.986122301514115, "children": { "UnityEnvironment._generate_step_input": { "total": 34.161149778541585, "count": 68939, "is_parallel": true, "self": 34.161149778541585 }, "communicator.exchange": { "total": 703.3213160878622, "count": 68939, "is_parallel": true, "self": 703.3213160878622 }, "steps_from_proto": { "total": 160.99490023349426, "count": 137878, "is_parallel": true, "self": 30.74429408972719, "children": { "_process_rank_one_or_two_observation": { "total": 130.25060614376707, "count": 551512, "is_parallel": true, "self": 130.25060614376707 } } } } } } } } } } }, "trainer_advance": { "total": 490.7362378152211, "count": 68940, "self": 13.820263071014779, "children": { "process_trajectory": { "total": 241.4395611682121, "count": 68940, "self": 240.9961185632128, "children": { "RLTrainer._checkpoint": { "total": 0.4434426049992908, "count": 2, "self": 0.4434426049992908 } } }, "_update_policy": { "total": 235.47641357599423, "count": 4, "self": 136.7342355200126, "children": { "TorchPOCAOptimizer.update": { "total": 98.74217805598164, "count": 120, "self": 98.74217805598164 } } } } } } }, "trainer_threads": { "total": 9.529976523481309e-07, "count": 1, "self": 9.529976523481309e-07 }, "TrainerController._save_models": { "total": 0.20355356299842242, "count": 1, "self": 0.0024367929981963243, "children": { "RLTrainer._checkpoint": { "total": 0.2011167700002261, "count": 1, "self": 0.2011167700002261 } } } } } } }