{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.4878665208816528, "min": 1.3633410930633545, "max": 3.2957427501678467, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 29328.82421875, "min": 15380.337890625, "max": 157225.328125, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 68.69014084507042, "min": 42.608695652173914, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19508.0, "min": 11684.0, "max": 28988.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1678.79115911589, "min": 1191.7092042587767, "max": 1712.6333279075886, "count": 4978 }, "SoccerTwos.Self-play.ELO.sum": { "value": 238388.34459445637, "min": 2384.1038029329357, "max": 371561.87747280765, "count": 4978 }, "SoccerTwos.Step.mean": { "value": 49999956.0, "min": 9510.0, "max": 49999956.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999956.0, "min": 9510.0, "max": 49999956.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.03689822927117348, "min": -0.15383467078208923, "max": 0.2077941596508026, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 5.27644681930542, "min": -25.382720947265625, "max": 35.36447525024414, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.03248460963368416, "min": -0.15733212232589722, "max": 0.20538489520549774, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 4.645299434661865, "min": -25.959800720214844, "max": 35.402835845947266, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.04424895023132538, "min": -0.5736823529005051, "max": 0.5353684221443377, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 6.327599883079529, "min": -77.66819989681244, "max": 76.77299976348877, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.04424895023132538, "min": -0.5736823529005051, "max": 0.5353684221443377, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 6.327599883079529, "min": -77.66819989681244, "max": 76.77299976348877, "count": 5000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.013809925685200142, "min": 0.010424467117991299, "max": 0.02779373701196164, "count": 2422 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.013809925685200142, "min": 0.010424467117991299, "max": 0.02779373701196164, "count": 2422 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09320181732376416, "min": 3.2134412170610934e-06, "max": 0.1227351687848568, "count": 2422 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09320181732376416, "min": 3.2134412170610934e-06, "max": 0.1227351687848568, "count": 2422 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09444441820184389, "min": 3.1553807540755466e-06, "max": 0.12522381494442622, "count": 2422 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09444441820184389, "min": 3.1553807540755466e-06, "max": 0.12522381494442622, "count": 2422 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2422 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2422 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 2422 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 2422 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 2422 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 2422 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1739224768", "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\\User\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1739329515" }, "total": 72341.1604107, "count": 1, "self": 1.163858900006744, "children": { "run_training.setup": { "total": 0.05425110000010136, "count": 1, "self": 0.05425110000010136 }, "TrainerController.start_learning": { "total": 72339.9423007, "count": 1, "self": 41.332624608898186, "children": { "TrainerController._reset_env": { "total": 8.761888399990312, "count": 250, "self": 8.761888399990312 }, "TrainerController.advance": { "total": 72289.75912639112, "count": 3422068, "self": 38.73894469419611, "children": { "env_step": { "total": 29453.363073493674, "count": 3422068, "self": 22957.408107901476, "children": { "SubprocessEnvManager._take_step": { "total": 6471.52508989032, "count": 3422068, "self": 247.30798628599132, "children": { "TorchPolicy.evaluate": { "total": 6224.217103604328, "count": 6282738, "self": 6224.217103604328 } } }, "workers": { "total": 24.429875701879155, "count": 3422068, "self": 0.0, "children": { "worker_root": { "total": 72281.87110799538, "count": 3422068, "is_parallel": true, "self": 53703.66807228551, "children": { "steps_from_proto": { "total": 0.22488129995736017, "count": 500, "is_parallel": true, "self": 0.04374559968596259, "children": { "_process_rank_one_or_two_observation": { "total": 0.18113570027139758, "count": 2000, "is_parallel": true, "self": 0.18113570027139758 } } }, "UnityEnvironment.step": { "total": 18577.97815440991, "count": 3422068, "is_parallel": true, "self": 846.730573420522, "children": { "UnityEnvironment._generate_step_input": { "total": 628.4532403943972, "count": 3422068, "is_parallel": true, "self": 628.4532403943972 }, "communicator.exchange": { "total": 14316.354748697075, "count": 3422068, "is_parallel": true, "self": 14316.354748697075 }, "steps_from_proto": { "total": 2786.439591897917, "count": 6844136, "is_parallel": true, "self": 541.6965623899123, "children": { "_process_rank_one_or_two_observation": { "total": 2244.743029508005, "count": 27376544, "is_parallel": true, "self": 2244.743029508005 } } } } } } } } } } }, "trainer_advance": { "total": 42797.657108203246, "count": 3422068, "self": 286.3806651967752, "children": { "process_trajectory": { "total": 6515.564624306407, "count": 3422068, "self": 6508.738010306368, "children": { "RLTrainer._checkpoint": { "total": 6.8266140000391715, "count": 100, "self": 6.8266140000391715 } } }, "_update_policy": { "total": 35995.71181870007, "count": 2422, "self": 3941.00679579992, "children": { "TorchPOCAOptimizer.update": { "total": 32054.705022900147, "count": 72672, "self": 32054.705022900147 } } } } } } }, "trainer_threads": { "total": 5.999900167807937e-07, "count": 1, "self": 5.999900167807937e-07 }, "TrainerController._save_models": { "total": 0.08866069999930914, "count": 1, "self": 0.022283399986918084, "children": { "RLTrainer._checkpoint": { "total": 0.06637730001239106, "count": 1, "self": 0.06637730001239106 } } } } } } }