{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.7826701402664185, "min": 1.7394626140594482, "max": 3.295732021331787, "count": 700 }, "SoccerTwos.Policy.Entropy.sum": { "value": 35482.265625, "min": 21054.87109375, "max": 105463.375, "count": 700 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 48.97979797979798, "min": 40.032786885245905, "max": 999.0, "count": 700 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19396.0, "min": 15772.0, "max": 25240.0, "count": 700 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1553.3871473543213, "min": 1200.6163275372303, "max": 1592.0030082153114, "count": 696 }, "SoccerTwos.Self-play.ELO.sum": { "value": 307570.6551761556, "min": 2401.619727385159, "max": 376258.17845454486, "count": 696 }, "SoccerTwos.Step.mean": { "value": 6999987.0, "min": 9636.0, "max": 6999987.0, "count": 700 }, "SoccerTwos.Step.sum": { "value": 6999987.0, "min": 9636.0, "max": 6999987.0, "count": 700 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.037391383200883865, "min": -0.09339915215969086, "max": 0.1686522513628006, "count": 700 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -7.440885543823242, "min": -17.465641021728516, "max": 24.960533142089844, "count": 700 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.039466168731451035, "min": -0.09576797485351562, "max": 0.16788546741008759, "count": 700 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -7.853767395019531, "min": -17.908611297607422, "max": 24.847049713134766, "count": 700 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 700 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 700 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.015877385834353653, "min": -0.5333333333333333, "max": 0.3762683899171891, "count": 700 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 3.159599781036377, "min": -53.84040021896362, "max": 58.32160043716431, "count": 700 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.015877385834353653, "min": -0.5333333333333333, "max": 0.3762683899171891, "count": 700 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 3.159599781036377, "min": -53.84040021896362, "max": 58.32160043716431, "count": 700 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 700 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 700 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016260930813991256, "min": 0.011429149822005356, "max": 0.022731703917088453, "count": 272 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016260930813991256, "min": 0.011429149822005356, "max": 0.022731703917088453, "count": 272 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10706143660677804, "min": 0.0011126294184344797, "max": 0.12248001620173454, "count": 272 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10706143660677804, "min": 0.0011126294184344797, "max": 0.12248001620173454, "count": 272 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10893148245910804, "min": 0.001181832811711595, "max": 0.12536103340486685, "count": 272 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10893148245910804, "min": 0.001181832811711595, "max": 0.12536103340486685, "count": 272 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 272 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 272 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000004, "min": 0.20000000000000004, "max": 0.20000000000000004, "count": 272 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000004, "min": 0.20000000000000004, "max": 0.20000000000000004, "count": 272 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 272 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 272 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1713786910", "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\\HP\\anaconda3\\envs\\unity_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": "2.2.2+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1713823638" }, "total": 36728.019763799966, "count": 1, "self": 3.8332122998544946, "children": { "run_training.setup": { "total": 0.18720070004928857, "count": 1, "self": 0.18720070004928857 }, "TrainerController.start_learning": { "total": 36723.99935080006, "count": 1, "self": 17.48002420598641, "children": { "TrainerController._reset_env": { "total": 23.18787780054845, "count": 35, "self": 23.18787780054845 }, "TrainerController.advance": { "total": 36682.99288069352, "count": 483487, "self": 18.02699136384763, "children": { "env_step": { "total": 14701.161438461975, "count": 483487, "self": 11609.348140965682, "children": { "SubprocessEnvManager._take_step": { "total": 3080.802714015823, "count": 483487, "self": 107.50193848169874, "children": { "TorchPolicy.evaluate": { "total": 2973.300775534124, "count": 880612, "self": 2973.300775534124 } } }, "workers": { "total": 11.010583480470814, "count": 483487, "self": 0.0, "children": { "worker_root": { "total": 36674.639397889725, "count": 483487, "is_parallel": true, "self": 27226.273161285208, "children": { "steps_from_proto": { "total": 0.10766420012805611, "count": 70, "is_parallel": true, "self": 0.02140469872392714, "children": { "_process_rank_one_or_two_observation": { "total": 0.08625950140412897, "count": 280, "is_parallel": true, "self": 0.08625950140412897 } } }, "UnityEnvironment.step": { "total": 9448.25857240439, "count": 483487, "is_parallel": true, "self": 553.870610109996, "children": { "UnityEnvironment._generate_step_input": { "total": 527.3979987687198, "count": 483487, "is_parallel": true, "self": 527.3979987687198 }, "communicator.exchange": { "total": 6613.873633601819, "count": 483487, "is_parallel": true, "self": 6613.873633601819 }, "steps_from_proto": { "total": 1753.1163299238542, "count": 966974, "is_parallel": true, "self": 336.6632152366219, "children": { "_process_rank_one_or_two_observation": { "total": 1416.4531146872323, "count": 3867896, "is_parallel": true, "self": 1416.4531146872323 } } } } } } } } } } }, "trainer_advance": { "total": 21963.804450867698, "count": 483487, "self": 111.99286475090776, "children": { "process_trajectory": { "total": 5004.217538817902, "count": 483487, "self": 5000.8038829177385, "children": { "RLTrainer._checkpoint": { "total": 3.413655900163576, "count": 14, "self": 3.413655900163576 } } }, "_update_policy": { "total": 16847.594047298888, "count": 272, "self": 1552.4214620952262, "children": { "TorchPOCAOptimizer.update": { "total": 15295.172585203662, "count": 9837, "self": 15295.172585203662 } } } } } } }, "trainer_threads": { "total": 3.100023604929447e-06, "count": 1, "self": 3.100023604929447e-06 }, "TrainerController._save_models": { "total": 0.338564999983646, "count": 1, "self": 0.08246479998342693, "children": { "RLTrainer._checkpoint": { "total": 0.25610020000021905, "count": 1, "self": 0.25610020000021905 } } } } } } }