{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.210845470428467, "min": 3.1426162719726562, "max": 3.2957265377044678, "count": 98 }, "SoccerTwos.Policy.Entropy.sum": { "value": 64114.1640625, "min": 30651.88671875, "max": 106849.734375, "count": 98 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 630.375, "min": 527.0, "max": 999.0, "count": 98 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20172.0, "min": 13164.0, "max": 28996.0, "count": 98 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1196.0805569769616, "min": 1189.1939078506243, "max": 1201.0212569856806, "count": 57 }, "SoccerTwos.Self-play.ELO.sum": { "value": 11960.805569769616, "min": 2378.3878157012487, "max": 16735.624095331375, "count": 57 }, "SoccerTwos.Step.mean": { "value": 979795.0, "min": 9514.0, "max": 979795.0, "count": 98 }, "SoccerTwos.Step.sum": { "value": 979795.0, "min": 9514.0, "max": 979795.0, "count": 98 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.0030385851860046387, "min": -0.007719757966697216, "max": 0.05610295385122299, "count": 98 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.04861736297607422, "min": -0.0834779143333435, "max": 0.7728978395462036, "count": 98 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.0028357012197375298, "min": -0.007596783805638552, "max": 0.056162890046834946, "count": 98 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.045371219515800476, "min": -0.08621978759765625, "max": 0.7466069459915161, "count": 98 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 98 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 98 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.13125000149011612, "min": -0.36363636363636365, "max": 0.2524285742214748, "count": 98 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -2.100000023841858, "min": -4.0, "max": 3.534000039100647, "count": 98 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.13125000149011612, "min": -0.36363636363636365, "max": 0.2524285742214748, "count": 98 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -2.100000023841858, "min": -4.0, "max": 3.534000039100647, "count": 98 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 98 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 98 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.014412013662513346, "min": 0.01167141782740752, "max": 0.0236203193916784, "count": 45 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.014412013662513346, "min": 0.01167141782740752, "max": 0.0236203193916784, "count": 45 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.001755226970029374, "min": 2.889044149393764e-07, "max": 0.0041265710179383555, "count": 45 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.001755226970029374, "min": 2.889044149393764e-07, "max": 0.0041265710179383555, "count": 45 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.001757680574276795, "min": 3.4516349908623546e-07, "max": 0.0037373302620835602, "count": 45 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.001757680574276795, "min": 3.4516349908623546e-07, "max": 0.0037373302620835602, "count": 45 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 45 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 45 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 45 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 45 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 45 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 45 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1710953840", "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\\hugol\\.conda\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/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": "2.2.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1710957346" }, "total": 3506.0894539, "count": 1, "self": 0.20364169999447768, "children": { "run_training.setup": { "total": 0.09287610000319546, "count": 1, "self": 0.09287610000319546 }, "TrainerController.start_learning": { "total": 3505.7929361000024, "count": 1, "self": 2.250120199751109, "children": { "TrainerController._reset_env": { "total": 4.4501137000006565, "count": 5, "self": 4.4501137000006565 }, "TrainerController.advance": { "total": 3498.873758000249, "count": 64093, "self": 2.6516102005698485, "children": { "env_step": { "total": 1712.45190959912, "count": 64093, "self": 1301.223486399027, "children": { "SubprocessEnvManager._take_step": { "total": 409.88517310016323, "count": 64093, "self": 15.577411601057975, "children": { "TorchPolicy.evaluate": { "total": 394.30776149910525, "count": 127322, "self": 394.30776149910525 } } }, "workers": { "total": 1.343250099929719, "count": 64093, "self": 0.0, "children": { "worker_root": { "total": 3492.1918439997644, "count": 64093, "is_parallel": true, "self": 2475.9199369002454, "children": { "steps_from_proto": { "total": 0.012400900006468873, "count": 10, "is_parallel": true, "self": 0.002701700013858499, "children": { "_process_rank_one_or_two_observation": { "total": 0.009699199992610374, "count": 40, "is_parallel": true, "self": 0.009699199992610374 } } }, "UnityEnvironment.step": { "total": 1016.2595061995125, "count": 64093, "is_parallel": true, "self": 50.63925389902579, "children": { "UnityEnvironment._generate_step_input": { "total": 45.77462260004904, "count": 64093, "is_parallel": true, "self": 45.77462260004904 }, "communicator.exchange": { "total": 749.0970755004455, "count": 64093, "is_parallel": true, "self": 749.0970755004455 }, "steps_from_proto": { "total": 170.7485541999922, "count": 128186, "is_parallel": true, "self": 35.36519909840354, "children": { "_process_rank_one_or_two_observation": { "total": 135.38335510158868, "count": 512744, "is_parallel": true, "self": 135.38335510158868 } } } } } } } } } } }, "trainer_advance": { "total": 1783.770238200559, "count": 64093, "self": 16.29433320087992, "children": { "process_trajectory": { "total": 283.2689534996898, "count": 64093, "self": 282.9338814996918, "children": { "RLTrainer._checkpoint": { "total": 0.3350719999980356, "count": 1, "self": 0.3350719999980356 } } }, "_update_policy": { "total": 1484.2069514999894, "count": 46, "self": 192.51356209997175, "children": { "TorchPOCAOptimizer.update": { "total": 1291.6933894000176, "count": 1352, "self": 1291.6933894000176 } } } } } } }, "trainer_threads": { "total": 1.3000026228837669e-06, "count": 1, "self": 1.3000026228837669e-06 }, "TrainerController._save_models": { "total": 0.21894289999909233, "count": 1, "self": 0.003208500002074288, "children": { "RLTrainer._checkpoint": { "total": 0.21573439999701804, "count": 1, "self": 0.21573439999701804 } } } } } } }