{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.1773006916046143, "min": 3.1694211959838867, "max": 3.295713424682617, "count": 253 }, "SoccerTwos.Policy.Entropy.sum": { "value": 70866.515625, "min": 17456.2421875, "max": 126067.296875, "count": 253 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 961.6666666666666, "min": 479.3, "max": 999.0, "count": 253 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 23080.0, "min": 16468.0, "max": 23576.0, "count": 253 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1207.453253061768, "min": 1194.2074292418765, "max": 1211.1198019546534, "count": 214 }, "SoccerTwos.Self-play.ELO.sum": { "value": 4829.813012247072, "min": 2391.0197751675187, "max": 19185.088451091804, "count": 214 }, "SoccerTwos.Step.mean": { "value": 2529978.0, "min": 9854.0, "max": 2529978.0, "count": 253 }, "SoccerTwos.Step.sum": { "value": 2529978.0, "min": 9854.0, "max": 2529978.0, "count": 253 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0035105810966342688, "min": -0.02522134780883789, "max": 0.05648775026202202, "count": 253 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.03861639276146889, "min": -0.30530762672424316, "max": 0.9602917432785034, "count": 253 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.003444874892011285, "min": -0.02424144372344017, "max": 0.05646296218037605, "count": 253 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.0378936231136322, "min": -0.2995484471321106, "max": 0.9598703384399414, "count": 253 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 253 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 253 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.04076363747431473, "min": -0.6666666666666666, "max": 0.2958857161658151, "count": 253 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.44840001221746206, "min": -10.0, "max": 4.142400026321411, "count": 253 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.04076363747431473, "min": -0.6666666666666666, "max": 0.2958857161658151, "count": 253 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.44840001221746206, "min": -10.0, "max": 4.142400026321411, "count": 253 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 253 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 253 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01752076644139985, "min": 0.010792954013838122, "max": 0.022604994444797435, "count": 118 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01752076644139985, "min": 0.010792954013838122, "max": 0.022604994444797435, "count": 118 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 7.653030940370323e-05, "min": 1.2674786451801387e-05, "max": 0.006809167750179768, "count": 118 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 7.653030940370323e-05, "min": 1.2674786451801387e-05, "max": 0.006809167750179768, "count": 118 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 7.562135645760767e-05, "min": 1.2772559208921545e-05, "max": 0.006838193613414963, "count": 118 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 7.562135645760767e-05, "min": 1.2772559208921545e-05, "max": 0.006838193613414963, "count": 118 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 9.999999999999998e-05, "min": 9.999999999999998e-05, "max": 9.999999999999998e-05, "count": 118 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 9.999999999999998e-05, "min": 9.999999999999998e-05, "max": 9.999999999999998e-05, "count": 118 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 118 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 118 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 118 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 118 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1713987941", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:34:57) [MSC v.1936 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\jelia\\anaconda3\\envs\\RL\\Scripts\\mlagents-learn SoccerTwos.yaml --env=./ml-agents/training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics", "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": "1713992717" }, "total": 4776.165138600045, "count": 1, "self": 4.22505030001048, "children": { "run_training.setup": { "total": 0.0901138000190258, "count": 1, "self": 0.0901138000190258 }, "TrainerController.start_learning": { "total": 4771.849974500015, "count": 1, "self": 3.146323976921849, "children": { "TrainerController._reset_env": { "total": 4.733260600012727, "count": 13, "self": 4.733260600012727 }, "TrainerController.advance": { "total": 4763.860005123075, "count": 165076, "self": 2.8971277381060645, "children": { "env_step": { "total": 2243.3683685733704, "count": 165076, "self": 1705.7382211600197, "children": { "SubprocessEnvManager._take_step": { "total": 535.6340368032688, "count": 165076, "self": 15.949296774109825, "children": { "TorchPolicy.evaluate": { "total": 519.684740029159, "count": 327638, "self": 519.684740029159 } } }, "workers": { "total": 1.9961106100818142, "count": 165075, "self": 0.0, "children": { "worker_root": { "total": 4764.844187174807, "count": 165075, "is_parallel": true, "self": 3467.9350290476577, "children": { "steps_from_proto": { "total": 0.01760899997316301, "count": 26, "is_parallel": true, "self": 0.0036862996639683843, "children": { "_process_rank_one_or_two_observation": { "total": 0.013922700309194624, "count": 104, "is_parallel": true, "self": 0.013922700309194624 } } }, "UnityEnvironment.step": { "total": 1296.8915491271764, "count": 165075, "is_parallel": true, "self": 64.45316591509618, "children": { "UnityEnvironment._generate_step_input": { "total": 58.14046540495474, "count": 165075, "is_parallel": true, "self": 58.14046540495474 }, "communicator.exchange": { "total": 955.3645186183276, "count": 165075, "is_parallel": true, "self": 955.3645186183276 }, "steps_from_proto": { "total": 218.93339918879792, "count": 330150, "is_parallel": true, "self": 44.952608693623915, "children": { "_process_rank_one_or_two_observation": { "total": 173.980790495174, "count": 1320600, "is_parallel": true, "self": 173.980790495174 } } } } } } } } } } }, "trainer_advance": { "total": 2517.5945088115986, "count": 165075, "self": 24.741489588748664, "children": { "process_trajectory": { "total": 350.5282766233431, "count": 165075, "self": 349.98508012352977, "children": { "RLTrainer._checkpoint": { "total": 0.543196499813348, "count": 5, "self": 0.543196499813348 } } }, "_update_policy": { "total": 2142.324742599507, "count": 118, "self": 305.5459926010808, "children": { "TorchPOCAOptimizer.update": { "total": 1836.778749998426, "count": 3540, "self": 1836.778749998426 } } } } } } }, "trainer_threads": { "total": 1.00000761449337e-06, "count": 1, "self": 1.00000761449337e-06 }, "TrainerController._save_models": { "total": 0.11038379999808967, "count": 1, "self": 0.0019347999477759004, "children": { "RLTrainer._checkpoint": { "total": 0.10844900005031377, "count": 1, "self": 0.10844900005031377 } } } } } } }