{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.194779396057129, "min": 3.194779396057129, "max": 3.2957358360290527, "count": 10 }, "SoccerTwos.Policy.Entropy.sum": { "value": 54387.92578125, "min": 21098.19921875, "max": 105463.546875, "count": 10 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 825.1666666666666, "min": 529.0, "max": 999.0, "count": 10 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19804.0, "min": 4408.0, "max": 31968.0, "count": 10 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1204.9447023646783, "min": 1200.1686945228769, "max": 1204.9447023646783, "count": 8 }, "SoccerTwos.Self-play.ELO.sum": { "value": 4819.778809458713, "min": 2400.45572274974, "max": 19279.115237834852, "count": 8 }, "SoccerTwos.Step.mean": { "value": 99326.0, "min": 9004.0, "max": 99326.0, "count": 10 }, "SoccerTwos.Step.sum": { "value": 99326.0, "min": 9004.0, "max": 99326.0, "count": 10 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0391935296356678, "min": -0.09667043387889862, "max": -0.0391935296356678, "count": 10 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.4703223705291748, "min": -1.2567156553268433, "max": -0.4703223705291748, "count": 10 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.039771754294633865, "min": -0.09674699604511261, "max": -0.039771754294633865, "count": 10 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.4772610664367676, "min": -1.2577109336853027, "max": -0.4772610664367676, "count": 10 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 10 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 10 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.11746666828791301, "min": -0.16666666666666666, "max": 0.27335555685891044, "count": 10 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -1.409600019454956, "min": -2.6535999923944473, "max": 4.920400023460388, "count": 10 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.11746666828791301, "min": -0.16666666666666666, "max": 0.27335555685891044, "count": 10 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -1.409600019454956, "min": -2.6535999923944473, "max": 4.920400023460388, "count": 10 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01701215987550313, "min": 0.01701215987550313, "max": 0.01785069198042038, "count": 4 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01701215987550313, "min": 0.01701215987550313, "max": 0.01785069198042038, "count": 4 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.002974525761674158, "min": 0.0013404503932598834, "max": 0.002974525761674158, "count": 4 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.002974525761674158, "min": 0.0013404503932598834, "max": 0.002974525761674158, "count": 4 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.004786403400357813, "min": 0.00133729571400461, "max": 0.004786403400357813, "count": 4 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.004786403400357813, "min": 0.00133729571400461, "max": 0.004786403400357813, "count": 4 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.00030000000000000003, "min": 0.0003, "max": 0.00030000000000000003, "count": 4 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.00030000000000000003, "min": 0.0003, "max": 0.00030000000000000003, "count": 4 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.19999999999999996, "min": 0.19999999999999996, "max": 0.19999999999999998, "count": 4 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.19999999999999996, "min": 0.19999999999999996, "max": 0.19999999999999998, "count": 4 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.004999999999999999, "min": 0.004999999999999999, "max": 0.005, "count": 4 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.004999999999999999, "min": 0.004999999999999999, "max": 0.005, "count": 4 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1700598600", "python_version": "3.10.7 (tags/v3.10.7:6cc6b13, Sep 5 2022, 14:08:36) [MSC v.1933 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\pierr\\AppData\\Local\\Programs\\Python\\Python310\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1700599281" }, "total": 680.8705422999992, "count": 1, "self": 3.6039944000003743, "children": { "run_training.setup": { "total": 0.3649790999988909, "count": 1, "self": 0.3649790999988909 }, "TrainerController.start_learning": { "total": 676.9015688, "count": 1, "self": 0.15478710010393115, "children": { "TrainerController._reset_env": { "total": 92.01418780000131, "count": 1, "self": 92.01418780000131 }, "TrainerController.advance": { "total": 583.5713514998952, "count": 6628, "self": 0.15925159994367277, "children": { "env_step": { "total": 148.90848049992383, "count": 6628, "self": 115.91590860013093, "children": { "SubprocessEnvManager._take_step": { "total": 32.88616669990188, "count": 6628, "self": 1.064480700139029, "children": { "TorchPolicy.evaluate": { "total": 31.82168599976285, "count": 13174, "self": 31.82168599976285 } } }, "workers": { "total": 0.10640519989101449, "count": 6628, "self": 0.0, "children": { "worker_root": { "total": 590.3726577000107, "count": 6628, "is_parallel": true, "self": 495.1535770999835, "children": { "steps_from_proto": { "total": 0.004433299996890128, "count": 2, "is_parallel": true, "self": 0.0005489999930432532, "children": { "_process_rank_one_or_two_observation": { "total": 0.0038843000038468745, "count": 8, "is_parallel": true, "self": 0.0038843000038468745 } } }, "UnityEnvironment.step": { "total": 95.21464730003026, "count": 6628, "is_parallel": true, "self": 4.748324800057162, "children": { "UnityEnvironment._generate_step_input": { "total": 3.5162811000082, "count": 6628, "is_parallel": true, "self": 3.5162811000082 }, "communicator.exchange": { "total": 72.12455299993235, "count": 6628, "is_parallel": true, "self": 72.12455299993235 }, "steps_from_proto": { "total": 14.825488400032555, "count": 13256, "is_parallel": true, "self": 2.8163953002786, "children": { "_process_rank_one_or_two_observation": { "total": 12.009093099753954, "count": 53024, "is_parallel": true, "self": 12.009093099753954 } } } } } } } } } } }, "trainer_advance": { "total": 434.5036194000277, "count": 6628, "self": 1.4871264000812516, "children": { "process_trajectory": { "total": 24.20115419994727, "count": 6628, "self": 24.20115419994727 }, "_update_policy": { "total": 408.81533879999915, "count": 4, "self": 36.99671610000223, "children": { "TorchPOCAOptimizer.update": { "total": 371.8186226999969, "count": 430, "self": 371.8186226999969 } } } } } } }, "trainer_threads": { "total": 8.999995770864189e-07, "count": 1, "self": 8.999995770864189e-07 }, "TrainerController._save_models": { "total": 1.16124149999996, "count": 1, "self": 0.010876599999392056, "children": { "RLTrainer._checkpoint": { "total": 1.150364900000568, "count": 1, "self": 1.150364900000568 } } } } } } }