{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.2236862182617188, "min": 2.2236862182617188, "max": 3.2957189083099365, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 44189.09375, "min": 14589.154296875, "max": 131304.375, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 50.75257731958763, "min": 45.31481481481482, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19692.0, "min": 16060.0, "max": 25120.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1433.741364077172, "min": 1189.5956165565858, "max": 1441.3301143214321, "count": 459 }, "SoccerTwos.Self-play.ELO.sum": { "value": 278145.82463097136, "min": 2380.9228634972515, "max": 307205.04548612237, "count": 459 }, "SoccerTwos.Step.mean": { "value": 4999960.0, "min": 9582.0, "max": 4999960.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999960.0, "min": 9582.0, "max": 4999960.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.0008088129106909037, "min": -0.09007861465215683, "max": 0.17856065928936005, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.15690970420837402, "min": -11.124003410339355, "max": 26.248416900634766, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.00015627108223270625, "min": -0.09853687137365341, "max": 0.18957993388175964, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.030316591262817383, "min": -11.725887298583984, "max": 27.868249893188477, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.13627422716199739, "min": -0.6320727271112528, "max": 0.4044249914586544, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -26.43720006942749, "min": -54.732399582862854, "max": 46.549999713897705, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.13627422716199739, "min": -0.6320727271112528, "max": 0.4044249914586544, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -26.43720006942749, "min": -54.732399582862854, "max": 46.549999713897705, "count": 500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01867120385480424, "min": 0.010484538082770693, "max": 0.024648681958206, "count": 237 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01867120385480424, "min": 0.010484538082770693, "max": 0.024648681958206, "count": 237 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08592734212676684, "min": 5.916356495087408e-07, "max": 0.10996115331848462, "count": 237 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.08592734212676684, "min": 5.916356495087408e-07, "max": 0.10996115331848462, "count": 237 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.08754756301641464, "min": 5.364527368101335e-07, "max": 0.11275291840235392, "count": 237 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.08754756301641464, "min": 5.364527368101335e-07, "max": 0.11275291840235392, "count": 237 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 237 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 237 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 237 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 237 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 237 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 237 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1717621701", "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\\wte42\\miniconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/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": "2.3.0+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1717659134" }, "total": 37432.35976200004, "count": 1, "self": 1.847334000049159, "children": { "run_training.setup": { "total": 0.14009329996770248, "count": 1, "self": 0.14009329996770248 }, "TrainerController.start_learning": { "total": 37430.37233470002, "count": 1, "self": 12.470843218325172, "children": { "TrainerController._reset_env": { "total": 9.234925400291104, "count": 25, "self": 9.234925400291104 }, "TrainerController.advance": { "total": 37408.39564098138, "count": 331820, "self": 11.010455687530339, "children": { "env_step": { "total": 11962.159047406283, "count": 331820, "self": 9005.196445814974, "children": { "SubprocessEnvManager._take_step": { "total": 2949.2028237767518, "count": 331820, "self": 72.86975739320042, "children": { "TorchPolicy.evaluate": { "total": 2876.3330663835513, "count": 638796, "self": 2876.3330663835513 } } }, "workers": { "total": 7.75977781455731, "count": 331820, "self": 0.0, "children": { "worker_root": { "total": 37408.51169527514, "count": 331820, "is_parallel": true, "self": 30325.816897982208, "children": { "steps_from_proto": { "total": 0.08698340010596439, "count": 50, "is_parallel": true, "self": 0.016030400583986193, "children": { "_process_rank_one_or_two_observation": { "total": 0.0709529995219782, "count": 200, "is_parallel": true, "self": 0.0709529995219782 } } }, "UnityEnvironment.step": { "total": 7082.607813892828, "count": 331820, "is_parallel": true, "self": 344.06576219026465, "children": { "UnityEnvironment._generate_step_input": { "total": 392.9229094006005, "count": 331820, "is_parallel": true, "self": 392.9229094006005 }, "communicator.exchange": { "total": 4993.341738008545, "count": 331820, "is_parallel": true, "self": 4993.341738008545 }, "steps_from_proto": { "total": 1352.277404293418, "count": 663640, "is_parallel": true, "self": 229.38437040668214, "children": { "_process_rank_one_or_two_observation": { "total": 1122.8930338867358, "count": 2654560, "is_parallel": true, "self": 1122.8930338867358 } } } } } } } } } } }, "trainer_advance": { "total": 25435.22613788757, "count": 331820, "self": 87.02087350736838, "children": { "process_trajectory": { "total": 2814.760318780085, "count": 331820, "self": 2812.3716234801686, "children": { "RLTrainer._checkpoint": { "total": 2.388695299916435, "count": 10, "self": 2.388695299916435 } } }, "_update_policy": { "total": 22533.444945600117, "count": 237, "self": 1808.1927846987383, "children": { "TorchPOCAOptimizer.update": { "total": 20725.25216090138, "count": 7110, "self": 20725.25216090138 } } } } } } }, "trainer_threads": { "total": 1.600012183189392e-06, "count": 1, "self": 1.600012183189392e-06 }, "TrainerController._save_models": { "total": 0.2709235000074841, "count": 1, "self": 0.031671400007326156, "children": { "RLTrainer._checkpoint": { "total": 0.23925210000015795, "count": 1, "self": 0.23925210000015795 } } } } } } }