{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.5944106578826904, "min": 1.5523359775543213, "max": 3.2958033084869385, "count": 1225 }, "SoccerTwos.Policy.Entropy.sum": { "value": 32296.3828125, "min": 23855.515625, "max": 111779.25, "count": 1225 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 50.84375, "min": 40.00819672131148, "max": 999.0, "count": 1225 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19524.0, "min": 14784.0, "max": 24308.0, "count": 1225 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1624.8321647038865, "min": 1199.6221507045457, "max": 1671.7046677195688, "count": 1220 }, "SoccerTwos.Self-play.ELO.sum": { "value": 311967.7756231462, "min": 2405.6430300703573, "max": 399398.3464361044, "count": 1220 }, "SoccerTwos.Step.mean": { "value": 12249967.0, "min": 9028.0, "max": 12249967.0, "count": 1225 }, "SoccerTwos.Step.sum": { "value": 12249967.0, "min": 9028.0, "max": 12249967.0, "count": 1225 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.03703314810991287, "min": -0.14056441187858582, "max": 0.22238922119140625, "count": 1225 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -7.147397518157959, "min": -27.61072540283203, "max": 32.0240478515625, "count": 1225 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.03805306553840637, "min": -0.1397092342376709, "max": 0.2204115092754364, "count": 1225 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -7.344241619110107, "min": -26.722496032714844, "max": 31.7392578125, "count": 1225 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1225 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1225 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.02380207319951428, "min": -0.4663232875196901, "max": 0.5156186070553092, "count": 1225 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -4.593800127506256, "min": -68.08319997787476, "max": 62.225200057029724, "count": 1225 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.02380207319951428, "min": -0.4663232875196901, "max": 0.5156186070553092, "count": 1225 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -4.593800127506256, "min": -68.08319997787476, "max": 62.225200057029724, "count": 1225 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1225 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1225 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01771582838264294, "min": 0.00927253424791464, "max": 0.027152934554032983, "count": 593 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01771582838264294, "min": 0.00927253424791464, "max": 0.027152934554032983, "count": 593 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.1201795868575573, "min": 0.0004942600581368122, "max": 0.1252055620153745, "count": 593 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.1201795868575573, "min": 0.0004942600581368122, "max": 0.1252055620153745, "count": 593 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.12245746826132138, "min": 0.0004948582233434232, "max": 0.12910691797733306, "count": 593 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.12245746826132138, "min": 0.0004948582233434232, "max": 0.12910691797733306, "count": 593 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 593 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 593 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 593 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 593 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 593 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 593 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1711136331", "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\\pepij\\miniconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./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": "2.2.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1711184498" }, "total": 48166.4502304, "count": 1, "self": 1.6270268999869586, "children": { "run_training.setup": { "total": 0.1658729000009771, "count": 1, "self": 0.1658729000009771 }, "TrainerController.start_learning": { "total": 48164.65733060001, "count": 1, "self": 23.67434030008735, "children": { "TrainerController._reset_env": { "total": 6.858543299989833, "count": 62, "self": 6.858543299989833 }, "TrainerController.advance": { "total": 48133.91878429993, "count": 845144, "self": 24.275168802327244, "children": { "env_step": { "total": 19578.120190499903, "count": 845144, "self": 15207.05279259734, "children": { "SubprocessEnvManager._take_step": { "total": 4355.861422203514, "count": 845144, "self": 135.66776299770572, "children": { "TorchPolicy.evaluate": { "total": 4220.193659205808, "count": 1538278, "self": 4220.193659205808 } } }, "workers": { "total": 15.205975699049304, "count": 845143, "self": 0.0, "children": { "worker_root": { "total": 48128.24973430014, "count": 845143, "is_parallel": true, "self": 35774.586721700856, "children": { "steps_from_proto": { "total": 0.14205029993172502, "count": 124, "is_parallel": true, "self": 0.028072700020857155, "children": { "_process_rank_one_or_two_observation": { "total": 0.11397759991086787, "count": 496, "is_parallel": true, "self": 0.11397759991086787 } } }, "UnityEnvironment.step": { "total": 12353.52096229935, "count": 845143, "is_parallel": true, "self": 660.7667581980386, "children": { "UnityEnvironment._generate_step_input": { "total": 536.610309003514, "count": 845143, "is_parallel": true, "self": 536.610309003514 }, "communicator.exchange": { "total": 9062.043905095452, "count": 845143, "is_parallel": true, "self": 9062.043905095452 }, "steps_from_proto": { "total": 2094.0999900023453, "count": 1690286, "is_parallel": true, "self": 406.68977941068806, "children": { "_process_rank_one_or_two_observation": { "total": 1687.4102105916572, "count": 6761144, "is_parallel": true, "self": 1687.4102105916572 } } } } } } } } } } }, "trainer_advance": { "total": 28531.5234249977, "count": 845143, "self": 164.42647359612238, "children": { "process_trajectory": { "total": 8793.229364001443, "count": 845143, "self": 8788.734475101439, "children": { "RLTrainer._checkpoint": { "total": 4.494888900004298, "count": 24, "self": 4.494888900004298 } } }, "_update_policy": { "total": 19573.867587400135, "count": 593, "self": 2101.598897700118, "children": { "TorchPOCAOptimizer.update": { "total": 17472.268689700017, "count": 17790, "self": 17472.268689700017 } } } } } } }, "trainer_threads": { "total": 1.8999999156221747e-06, "count": 1, "self": 1.8999999156221747e-06 }, "TrainerController._save_models": { "total": 0.20566079999844078, "count": 1, "self": 0.009602600010111928, "children": { "RLTrainer._checkpoint": { "total": 0.19605819998832885, "count": 1, "self": 0.19605819998832885 } } } } } } }