{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.924513816833496, "min": 2.9243216514587402, "max": 3.1757395267486572, "count": 191 }, "SoccerTwos.Policy.Entropy.sum": { "value": 59800.4609375, "min": 21701.421875, "max": 108982.8125, "count": 191 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 63.5921052631579, "min": 63.31578947368421, "max": 999.0, "count": 191 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19332.0, "min": 10160.0, "max": 27560.0, "count": 191 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1617.6138335183207, "min": 1465.5792810382482, "max": 1621.2473854295308, "count": 188 }, "SoccerTwos.Self-play.ELO.sum": { "value": 245877.30269478474, "min": 2937.1881736318173, "max": 251714.78348813194, "count": 188 }, "SoccerTwos.Step.mean": { "value": 7959959.0, "min": 6059598.0, "max": 7959959.0, "count": 191 }, "SoccerTwos.Step.sum": { "value": 7959959.0, "min": 6059598.0, "max": 7959959.0, "count": 191 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.04880588874220848, "min": -0.05066097900271416, "max": 0.08102425932884216, "count": 191 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 7.418495178222656, "min": -4.516129970550537, "max": 12.072614669799805, "count": 191 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.03905719891190529, "min": -0.052238672971725464, "max": 0.07591870427131653, "count": 191 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 5.936694145202637, "min": -4.706704616546631, "max": 11.156150817871094, "count": 191 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 191 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 191 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.00046316102931374, "min": -0.6333142859595162, "max": 0.5846869556800179, "count": 191 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -0.07040047645568848, "min": -29.858399868011475, "max": 34.659199953079224, "count": 191 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.00046316102931374, "min": -0.6333142859595162, "max": 0.5846869556800179, "count": 191 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -0.07040047645568848, "min": -29.858399868011475, "max": 34.659199953079224, "count": 191 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 191 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 191 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.02058447713206988, "min": 0.010780977704174195, "max": 0.022938029281795023, "count": 90 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.02058447713206988, "min": 0.010780977704174195, "max": 0.022938029281795023, "count": 90 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08732584243019421, "min": 0.0024408352658307803, "max": 0.08789002100626628, "count": 90 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.08732584243019421, "min": 0.0024408352658307803, "max": 0.08789002100626628, "count": 90 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09296473537882169, "min": 0.002443784166825935, "max": 0.09296473537882169, "count": 90 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09296473537882169, "min": 0.002443784166825935, "max": 0.09296473537882169, "count": 90 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 2.9999999999999994e-05, "min": 2.9999999999999994e-05, "max": 2.9999999999999994e-05, "count": 90 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 2.9999999999999994e-05, "min": 2.9999999999999994e-05, "max": 2.9999999999999994e-05, "count": 90 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 90 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 90 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 90 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 90 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1677517845", "python_version": "3.9.16 (main, Jan 11 2023, 10:02:19) \n[Clang 14.0.6 ]", "command_line_arguments": "/opt/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.app --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0", "numpy_version": "1.21.2", "end_time_seconds": "1677525563" }, "total": 7718.523238541, "count": 1, "self": 0.23457920700002433, "children": { "run_training.setup": { "total": 0.011447624999999961, "count": 1, "self": 0.011447624999999961 }, "TrainerController.start_learning": { "total": 7718.277211709, "count": 1, "self": 1.4373726120520587, "children": { "TrainerController._reset_env": { "total": 2.735461289999651, "count": 11, "self": 2.735461289999651 }, "TrainerController.advance": { "total": 7713.895985764948, "count": 125343, "self": 1.2087337050425049, "children": { "env_step": { "total": 6006.109079993984, "count": 125343, "self": 5765.819425731842, "children": { "SubprocessEnvManager._take_step": { "total": 239.32615655607444, "count": 125343, "self": 6.2316118882702085, "children": { "TorchPolicy.evaluate": { "total": 233.09454466780423, "count": 242926, "self": 233.09454466780423 } } }, "workers": { "total": 0.9634977060677823, "count": 125342, "self": 0.0, "children": { "worker_root": { "total": 7713.243843144198, "count": 125342, "is_parallel": true, "self": 2119.454057478116, "children": { "steps_from_proto": { "total": 0.01738087400010313, "count": 22, "is_parallel": true, "self": 0.002072127000050994, "children": { "_process_rank_one_or_two_observation": { "total": 0.015308747000052136, "count": 88, "is_parallel": true, "self": 0.015308747000052136 } } }, "UnityEnvironment.step": { "total": 5593.772404792082, "count": 125342, "is_parallel": true, "self": 15.628556695811312, "children": { "UnityEnvironment._generate_step_input": { "total": 100.16159577592992, "count": 125342, "is_parallel": true, "self": 100.16159577592992 }, "communicator.exchange": { "total": 5259.308347307049, "count": 125342, "is_parallel": true, "self": 5259.308347307049 }, "steps_from_proto": { "total": 218.6739050132917, "count": 250684, "is_parallel": true, "self": 23.00034468647317, "children": { "_process_rank_one_or_two_observation": { "total": 195.67356032681852, "count": 1002736, "is_parallel": true, "self": 195.67356032681852 } } } } } } } } } } }, "trainer_advance": { "total": 1706.5781720659218, "count": 125342, "self": 13.638485148922427, "children": { "process_trajectory": { "total": 241.91218341999755, "count": 125342, "self": 241.3605262119975, "children": { "RLTrainer._checkpoint": { "total": 0.5516572080000515, "count": 3, "self": 0.5516572080000515 } } }, "_update_policy": { "total": 1451.0275034970018, "count": 90, "self": 151.5602755720074, "children": { "TorchPOCAOptimizer.update": { "total": 1299.4672279249944, "count": 2700, "self": 1299.4672279249944 } } } } } } }, "trainer_threads": { "total": 5.420006345957518e-07, "count": 1, "self": 5.420006345957518e-07 }, "TrainerController._save_models": { "total": 0.20839149999937945, "count": 1, "self": 0.0013525839995054412, "children": { "RLTrainer._checkpoint": { "total": 0.207038915999874, "count": 1, "self": 0.207038915999874 } } } } } } }