{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.5598649978637695, "min": 1.4148043394088745, "max": 3.2957513332366943, "count": 3124 }, "SoccerTwos.Policy.Entropy.sum": { "value": 29300.50390625, "min": 16600.056640625, "max": 149917.59375, "count": 3124 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 65.76315789473684, "min": 40.586776859504134, "max": 999.0, "count": 3124 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19992.0, "min": 1200.0, "max": 30420.0, "count": 3124 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1744.630578303296, "min": 1178.241648118888, "max": 1763.201907177039, "count": 3095 }, "SoccerTwos.Self-play.ELO.sum": { "value": 265183.847902101, "min": 2356.483296237776, "max": 401242.281178166, "count": 3095 }, "SoccerTwos.Step.mean": { "value": 31239980.0, "min": 9440.0, "max": 31239980.0, "count": 3124 }, "SoccerTwos.Step.sum": { "value": 31239980.0, "min": 9440.0, "max": 31239980.0, "count": 3124 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.004775442648679018, "min": -0.17131519317626953, "max": 0.22156104445457458, "count": 3124 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.7210918068885803, "min": -24.326757431030273, "max": 32.56947326660156, "count": 3124 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.00278552807867527, "min": -0.16930297017097473, "max": 0.21557892858982086, "count": 3124 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.42061474919319153, "min": -24.06451416015625, "max": 31.690101623535156, "count": 3124 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 3124 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 3124 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.01713377632052693, "min": -0.6, "max": 0.5466086924400019, "count": 3124 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -2.5872002243995667, "min": -64.31620037555695, "max": 50.80800008773804, "count": 3124 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.01713377632052693, "min": -0.6, "max": 0.5466086924400019, "count": 3124 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -2.5872002243995667, "min": -64.31620037555695, "max": 50.80800008773804, "count": 3124 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3124 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3124 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017738105164607988, "min": 0.010973652174773937, "max": 0.024367449737231556, "count": 1512 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017738105164607988, "min": 0.010973652174773937, "max": 0.024367449737231556, "count": 1512 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10335170576969782, "min": 3.163041189206221e-06, "max": 0.1284737418095271, "count": 1512 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10335170576969782, "min": 3.163041189206221e-06, "max": 0.1284737418095271, "count": 1512 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10453864932060242, "min": 3.2997339189932973e-06, "max": 0.13083223700523378, "count": 1512 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10453864932060242, "min": 3.2997339189932973e-06, "max": 0.13083223700523378, "count": 1512 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1512 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1512 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 1512 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 1512 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 1512 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 1512 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1740983605", "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\\mechmofo\\.conda\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1741029112" }, "total": 45507.78440250001, "count": 1, "self": 1.0283526000130223, "children": { "run_training.setup": { "total": 0.06862109999929089, "count": 1, "self": 0.06862109999929089 }, "TrainerController.start_learning": { "total": 45506.687428799996, "count": 1, "self": 40.53003490436822, "children": { "TrainerController._reset_env": { "total": 6.264219500029867, "count": 157, "self": 6.264219500029867 }, "TrainerController.advance": { "total": 45459.74290179561, "count": 2160408, "self": 38.56875520146423, "children": { "env_step": { "total": 32253.99747030285, "count": 2160408, "self": 18753.824297593797, "children": { "SubprocessEnvManager._take_step": { "total": 13475.990711609797, "count": 2160408, "self": 231.60722509941115, "children": { "TorchPolicy.evaluate": { "total": 13244.383486510385, "count": 3926496, "self": 13244.383486510385 } } }, "workers": { "total": 24.182461099255306, "count": 2160407, "self": 0.0, "children": { "worker_root": { "total": 45453.943528405434, "count": 2160407, "is_parallel": true, "self": 30874.416574208873, "children": { "steps_from_proto": { "total": 0.18851700005325256, "count": 314, "is_parallel": true, "self": 0.037206400142167695, "children": { "_process_rank_one_or_two_observation": { "total": 0.15131059991108486, "count": 1256, "is_parallel": true, "self": 0.15131059991108486 } } }, "UnityEnvironment.step": { "total": 14579.338437196508, "count": 2160407, "is_parallel": true, "self": 705.5183977148263, "children": { "UnityEnvironment._generate_step_input": { "total": 603.0071491958151, "count": 2160407, "is_parallel": true, "self": 603.0071491958151 }, "communicator.exchange": { "total": 10929.271967792018, "count": 2160407, "is_parallel": true, "self": 10929.271967792018 }, "steps_from_proto": { "total": 2341.5409224938485, "count": 4320814, "is_parallel": true, "self": 477.9007207722243, "children": { "_process_rank_one_or_two_observation": { "total": 1863.6402017216242, "count": 17283256, "is_parallel": true, "self": 1863.6402017216242 } } } } } } } } } } }, "trainer_advance": { "total": 13167.176676291296, "count": 2160407, "self": 261.0154291885701, "children": { "process_trajectory": { "total": 6870.0783336030145, "count": 2160407, "self": 6860.200931202991, "children": { "RLTrainer._checkpoint": { "total": 9.87740240002313, "count": 62, "self": 9.87740240002313 } } }, "_update_policy": { "total": 6036.082913499711, "count": 1513, "self": 3488.6145823999395, "children": { "TorchPOCAOptimizer.update": { "total": 2547.4683310997716, "count": 45402, "self": 2547.4683310997716 } } } } } } }, "trainer_threads": { "total": 3.2999960239976645e-06, "count": 1, "self": 3.2999960239976645e-06 }, "TrainerController._save_models": { "total": 0.15026929999294225, "count": 1, "self": 0.036373599999933504, "children": { "RLTrainer._checkpoint": { "total": 0.11389569999300875, "count": 1, "self": 0.11389569999300875 } } } } } } }