{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.9415829181671143, "min": 2.9415829181671143, "max": 2.9415829181671143, "count": 1 }, "SoccerTwos.Policy.Entropy.sum": { "value": 460487.15625, "min": 460487.15625, "max": 460487.15625, "count": 1 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 111.38297872340425, "min": 111.38297872340425, "max": 111.38297872340425, "count": 1 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20940.0, "min": 20940.0, "max": 20940.0, "count": 1 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1203.3920947656047, "min": 1203.3920947656047, "max": 1203.3920947656047, "count": 1 }, "SoccerTwos.Self-play.ELO.sum": { "value": 55356.03635921782, "min": 55356.03635921782, "max": 55356.03635921782, "count": 1 }, "SoccerTwos.Step.mean": { "value": 9836.0, "min": 9836.0, "max": 9836.0, "count": 1 }, "SoccerTwos.Step.sum": { "value": 9836.0, "min": 9836.0, "max": 9836.0, "count": 1 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.046986013650894165, "min": -0.046986013650894165, "max": -0.046986013650894165, "count": 1 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -4.322713375091553, "min": -4.322713375091553, "max": -4.322713375091553, "count": 1 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.04885184392333031, "min": -0.04885184392333031, "max": -0.04885184392333031, "count": 1 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -4.4943695068359375, "min": -4.4943695068359375, "max": -4.4943695068359375, "count": 1 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.17788695564250584, "min": -0.17788695564250584, "max": -0.17788695564250584, "count": 1 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -16.365599919110537, "min": -16.365599919110537, "max": -16.365599919110537, "count": 1 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.17788695564250584, "min": -0.17788695564250584, "max": -0.17788695564250584, "count": 1 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -16.365599919110537, "min": -16.365599919110537, "max": -16.365599919110537, "count": 1 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.2279435114503995, "min": 0.2279435114503995, "max": 0.2279435114503995, "count": 1 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 5.4706442748095885, "min": 5.4706442748095885, "max": 5.4706442748095885, "count": 1 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.005402487274283552, "min": 0.005402487274283552, "max": 0.005402487274283552, "count": 1 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.12965969458280524, "min": 0.12965969458280524, "max": 0.12965969458280524, "count": 1 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.01613315310505718, "min": 0.01613315310505718, "max": 0.01613315310505718, "count": 1 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.38719567452137227, "min": 0.38719567452137227, "max": 0.38719567452137227, "count": 1 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0072, "min": 0.0072, "max": 0.0072, "count": 1 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.19999999999999996, "min": 0.19999999999999996, "max": 0.19999999999999996, "count": 1 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 4.799999999999999, "min": 4.799999999999999, "max": 4.799999999999999, "count": 1 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005, "min": 0.005, "max": 0.005, "count": 1 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.12, "min": 0.12, "max": 0.12, "count": 1 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1720800030", "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\\ADMIN\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn C:/Users/ADMIN/for_machine_learning/for_machine_learning/ml/Learnings/deep_learning_tool_kits/Deep_RL/ml-agents/config/poca/SoccerTwos.yaml --env=C:/Users/ADMIN/for_machine_learning/for_machine_learning/ml/Learnings/deep_learning_tool_kits/Deep_RL/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1720800426" }, "total": 395.8422837999824, "count": 1, "self": 0.5873121999902651, "children": { "run_training.setup": { "total": 0.18558990000747144, "count": 1, "self": 0.18558990000747144 }, "TrainerController.start_learning": { "total": 395.06938169998466, "count": 1, "self": 0.23730519885430112, "children": { "TrainerController._reset_env": { "total": 11.153327699954389, "count": 40, "self": 11.153327699954389 }, "TrainerController.advance": { "total": 383.334124301211, "count": 4896, "self": 0.2583260011742823, "children": { "env_step": { "total": 188.8054977004067, "count": 4896, "self": 139.31214919898775, "children": { "SubprocessEnvManager._take_step": { "total": 49.34584840020398, "count": 4896, "self": 1.6539560005476233, "children": { "TorchPolicy.evaluate": { "total": 47.69189239965635, "count": 9784, "self": 47.69189239965635 } } }, "workers": { "total": 0.14750010121497326, "count": 4896, "self": 0.0, "children": { "worker_root": { "total": 386.6030013007403, "count": 4896, "is_parallel": true, "self": 278.12211950161145, "children": { "steps_from_proto": { "total": 0.16964630017173477, "count": 78, "is_parallel": true, "self": 0.03418659997987561, "children": { "_process_rank_one_or_two_observation": { "total": 0.13545970019185916, "count": 312, "is_parallel": true, "self": 0.13545970019185916 } } }, "UnityEnvironment.step": { "total": 108.3112354989571, "count": 4896, "is_parallel": true, "self": 6.270320098468801, "children": { "UnityEnvironment._generate_step_input": { "total": 6.085429701022804, "count": 4896, "is_parallel": true, "self": 6.085429701022804 }, "communicator.exchange": { "total": 74.54166550075752, "count": 4896, "is_parallel": true, "self": 74.54166550075752 }, "steps_from_proto": { "total": 21.41382019870798, "count": 9792, "is_parallel": true, "self": 4.229228097276064, "children": { "_process_rank_one_or_two_observation": { "total": 17.184592101431917, "count": 39168, "is_parallel": true, "self": 17.184592101431917 } } } } } } } } } } }, "trainer_advance": { "total": 194.27030059963, "count": 4896, "self": 0.9905304000130855, "children": { "process_trajectory": { "total": 7.081178599590203, "count": 4896, "self": 7.081178599590203 }, "_update_policy": { "total": 186.1985916000267, "count": 24, "self": 5.064732000144431, "children": { "TorchPOCAOptimizer.update": { "total": 181.13385959988227, "count": 2427, "self": 181.13385959988227 } } } } } } }, "trainer_threads": { "total": 2.5999906938523054e-06, "count": 1, "self": 2.5999906938523054e-06 }, "TrainerController._save_models": { "total": 0.3446218999742996, "count": 1, "self": 0.010635999991791323, "children": { "RLTrainer._checkpoint": { "total": 0.33398589998250827, "count": 1, "self": 0.33398589998250827 } } } } } } }