{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.8950600624084473, "min": 1.8428058624267578, "max": 3.2957427501678467, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 34505.25390625, "min": 12429.017578125, "max": 130210.375, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 49.97872340425532, "min": 41.5, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 18792.0, "min": 16312.0, "max": 24760.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1499.4921294900378, "min": 1195.1896208494968, "max": 1528.4352213754528, "count": 498 }, "SoccerTwos.Self-play.ELO.sum": { "value": 281904.5203441271, "min": 2390.8136482672194, "max": 351854.632104418, "count": 498 }, "SoccerTwos.Step.mean": { "value": 4999775.0, "min": 9400.0, "max": 4999775.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999775.0, "min": 9400.0, "max": 4999775.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.013545672409236431, "min": -0.098695307970047, "max": 0.13218095898628235, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 2.5601320266723633, "min": -19.442975997924805, "max": 21.919206619262695, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.015265977941453457, "min": -0.09554668515920639, "max": 0.13215751945972443, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 2.8852698802948, "min": -18.822696685791016, "max": 23.19841766357422, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.13644444500958477, "min": -0.6489799999631941, "max": 0.359280002117157, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 25.788000106811523, "min": -57.3491997718811, "max": 55.48639965057373, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.13644444500958477, "min": -0.6489799999631941, "max": 0.359280002117157, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 25.788000106811523, "min": -57.3491997718811, "max": 55.48639965057373, "count": 500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017967180290725082, "min": 0.010806732341006865, "max": 0.025368310267610165, "count": 239 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017967180290725082, "min": 0.010806732341006865, "max": 0.025368310267610165, "count": 239 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11515003864963849, "min": 0.0007502670230072302, "max": 0.12373966351151466, "count": 239 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11515003864963849, "min": 0.0007502670230072302, "max": 0.12373966351151466, "count": 239 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11650773634513219, "min": 0.0007690098856983241, "max": 0.12533981253703436, "count": 239 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11650773634513219, "min": 0.0007690098856983241, "max": 0.12533981253703436, "count": 239 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 239 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 239 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 239 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 239 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 239 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 239 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1717081154", "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\\luqma\\miniconda3\\envs\\rl\\Scripts\\mlagents-learn C:\\Users\\luqma\\ml-agents\\config\\poca\\SoccerTwos.yaml --env=C:\\Users\\luqma\\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": "2.3.0+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1717093917" }, "total": 12763.669642699999, "count": 1, "self": 0.2580960000050254, "children": { "run_training.setup": { "total": 0.10602999999537133, "count": 1, "self": 0.10602999999537133 }, "TrainerController.start_learning": { "total": 12763.305516699998, "count": 1, "self": 7.85644919986953, "children": { "TrainerController._reset_env": { "total": 13.895366399970953, "count": 25, "self": 13.895366399970953 }, "TrainerController.advance": { "total": 12741.434771400163, "count": 340414, "self": 7.019766296551097, "children": { "env_step": { "total": 5164.979889402413, "count": 340414, "self": 3941.6916681031435, "children": { "SubprocessEnvManager._take_step": { "total": 1218.3531910988822, "count": 340414, "self": 41.63772129654535, "children": { "TorchPolicy.evaluate": { "total": 1176.7154698023369, "count": 633302, "self": 1176.7154698023369 } } }, "workers": { "total": 4.9350302003877005, "count": 340414, "self": 0.0, "children": { "worker_root": { "total": 12740.590404199305, "count": 340414, "is_parallel": true, "self": 9697.703708599496, "children": { "steps_from_proto": { "total": 0.039804900021408685, "count": 50, "is_parallel": true, "self": 0.007993800012627617, "children": { "_process_rank_one_or_two_observation": { "total": 0.03181110000878107, "count": 200, "is_parallel": true, "self": 0.03181110000878107 } } }, "UnityEnvironment.step": { "total": 3042.8468906997878, "count": 340414, "is_parallel": true, "self": 166.06688000859867, "children": { "UnityEnvironment._generate_step_input": { "total": 147.1515138980758, "count": 340414, "is_parallel": true, "self": 147.1515138980758 }, "communicator.exchange": { "total": 2215.8349558035843, "count": 340414, "is_parallel": true, "self": 2215.8349558035843 }, "steps_from_proto": { "total": 513.793540989529, "count": 680828, "is_parallel": true, "self": 104.6684289896657, "children": { "_process_rank_one_or_two_observation": { "total": 409.1251119998633, "count": 2723312, "is_parallel": true, "self": 409.1251119998633 } } } } } } } } } } }, "trainer_advance": { "total": 7569.435115701199, "count": 340414, "self": 64.62112870129931, "children": { "process_trajectory": { "total": 1209.939918999822, "count": 340414, "self": 1208.6821608997998, "children": { "RLTrainer._checkpoint": { "total": 1.257758100022329, "count": 10, "self": 1.257758100022329 } } }, "_update_policy": { "total": 6294.874068000077, "count": 239, "self": 731.2173146002315, "children": { "TorchPOCAOptimizer.update": { "total": 5563.656753399846, "count": 7170, "self": 5563.656753399846 } } } } } } }, "trainer_threads": { "total": 1.1999945854768157e-06, "count": 1, "self": 1.1999945854768157e-06 }, "TrainerController._save_models": { "total": 0.11892850000003818, "count": 1, "self": 0.00748869999370072, "children": { "RLTrainer._checkpoint": { "total": 0.11143980000633746, "count": 1, "self": 0.11143980000633746 } } } } } } }