{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.8765040636062622, "min": 1.7863812446594238, "max": 3.2957403659820557, "count": 1000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 38130.5625, "min": 26096.654296875, "max": 124687.453125, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 56.81395348837209, "min": 40.834782608695654, "max": 999.0, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19544.0, "min": 7524.0, "max": 31968.0, "count": 1000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1708.697937470418, "min": 1193.9183309788523, "max": 1729.712270819381, "count": 977 }, "SoccerTwos.Self-play.ELO.sum": { "value": 293896.0452449119, "min": 2388.7747462231155, "max": 409305.8691895164, "count": 977 }, "SoccerTwos.Step.mean": { "value": 9999972.0, "min": 9522.0, "max": 9999972.0, "count": 1000 }, "SoccerTwos.Step.sum": { "value": 9999972.0, "min": 9522.0, "max": 9999972.0, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.018940679728984833, "min": -0.13247385621070862, "max": 0.1722002923488617, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -3.2577970027923584, "min": -31.263830184936523, "max": 27.035446166992188, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.016107002273201942, "min": -0.13530893623828888, "max": 0.1711462438106537, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -2.77040433883667, "min": -31.93290901184082, "max": 26.86996078491211, "count": 1000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.1569639527520468, "min": -0.5523571435894284, "max": 0.5504761849130902, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -26.99779987335205, "min": -63.495600044727325, "max": 68.06360018253326, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.1569639527520468, "min": -0.5523571435894284, "max": 0.5504761849130902, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -26.99779987335205, "min": -63.495600044727325, "max": 68.06360018253326, "count": 1000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01596075825897666, "min": 0.009748829703312367, "max": 0.02528138120736306, "count": 482 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01596075825897666, "min": 0.009748829703312367, "max": 0.02528138120736306, "count": 482 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11302952369054159, "min": 1.8284332175729407e-05, "max": 0.12636658623814584, "count": 482 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11302952369054159, "min": 1.8284332175729407e-05, "max": 0.12636658623814584, "count": 482 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11423842584093412, "min": 2.9556284274197728e-05, "max": 0.12823313375314077, "count": 482 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11423842584093412, "min": 2.9556284274197728e-05, "max": 0.12823313375314077, "count": 482 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 482 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 482 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 482 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 482 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 482 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 482 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1676205365", "python_version": "3.8.16 (default, Jan 17 2023, 22:25:28) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\Kaush\\miniconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=pocatrainergoal2 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.13.1+cu117", "numpy_version": "1.21.2", "end_time_seconds": "1676224341" }, "total": 18975.6975353, "count": 1, "self": 0.4365185000024212, "children": { "run_training.setup": { "total": 0.10058610000000012, "count": 1, "self": 0.10058610000000012 }, "TrainerController.start_learning": { "total": 18975.160430699998, "count": 1, "self": 16.110423399986757, "children": { "TrainerController._reset_env": { "total": 7.637262500006049, "count": 50, "self": 7.637262500006049 }, "TrainerController.advance": { "total": 18951.275029000004, "count": 687399, "self": 15.667838597910304, "children": { "env_step": { "total": 13553.667134001029, "count": 687399, "self": 8593.320714800799, "children": { "SubprocessEnvManager._take_step": { "total": 4950.316458399658, "count": 687399, "self": 88.2371188992447, "children": { "TorchPolicy.evaluate": { "total": 4862.079339500413, "count": 1259946, "self": 4862.079339500413 } } }, "workers": { "total": 10.02996080057262, "count": 687399, "self": 0.0, "children": { "worker_root": { "total": 18951.255278000794, "count": 687399, "is_parallel": true, "self": 12080.557430200377, "children": { "steps_from_proto": { "total": 0.08635440000356454, "count": 100, "is_parallel": true, "self": 0.019513299986659405, "children": { "_process_rank_one_or_two_observation": { "total": 0.06684110001690513, "count": 400, "is_parallel": true, "self": 0.06684110001690513 } } }, "UnityEnvironment.step": { "total": 6870.611493400413, "count": 687399, "is_parallel": true, "self": 299.2152722992032, "children": { "UnityEnvironment._generate_step_input": { "total": 302.0881656994367, "count": 687399, "is_parallel": true, "self": 302.0881656994367 }, "communicator.exchange": { "total": 5328.05041159995, "count": 687399, "is_parallel": true, "self": 5328.05041159995 }, "steps_from_proto": { "total": 941.2576438018222, "count": 1374798, "is_parallel": true, "self": 204.96093240318282, "children": { "_process_rank_one_or_two_observation": { "total": 736.2967113986393, "count": 5499192, "is_parallel": true, "self": 736.2967113986393 } } } } } } } } } } }, "trainer_advance": { "total": 5381.940056401063, "count": 687399, "self": 106.62313190166333, "children": { "process_trajectory": { "total": 2449.901281399413, "count": 687399, "self": 2446.799516599416, "children": { "RLTrainer._checkpoint": { "total": 3.101764799996772, "count": 20, "self": 3.101764799996772 } } }, "_update_policy": { "total": 2825.4156430999865, "count": 482, "self": 1816.062887099934, "children": { "TorchPOCAOptimizer.update": { "total": 1009.3527560000525, "count": 14469, "self": 1009.3527560000525 } } } } } } }, "trainer_threads": { "total": 1.0000003385357559e-06, "count": 1, "self": 1.0000003385357559e-06 }, "TrainerController._save_models": { "total": 0.1377147999992303, "count": 1, "self": 0.0013646000006701797, "children": { "RLTrainer._checkpoint": { "total": 0.13635019999856013, "count": 1, "self": 0.13635019999856013 } } } } } } }