{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.147136688232422, "min": 3.047994375228882, "max": 3.295745849609375, "count": 621 }, "SoccerTwos.Policy.Entropy.sum": { "value": 27694.802734375, "min": 15971.748046875, "max": 160773.265625, "count": 621 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 956.0, "min": 412.57142857142856, "max": 999.0, "count": 621 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19120.0, "min": 14576.0, "max": 25272.0, "count": 621 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1207.3728502053852, "min": 1197.745733216471, "max": 1218.3622745937141, "count": 384 }, "SoccerTwos.Self-play.ELO.sum": { "value": 4829.491400821541, "min": 2395.491466432942, "max": 16847.808579292, "count": 384 }, "SoccerTwos.Step.mean": { "value": 6209213.0, "min": 9652.0, "max": 6209213.0, "count": 621 }, "SoccerTwos.Step.sum": { "value": 6209213.0, "min": 9652.0, "max": 6209213.0, "count": 621 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.01980649121105671, "min": -0.10010386258363724, "max": 0.01263430342078209, "count": 621 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.1980649083852768, "min": -1.3013502359390259, "max": 0.16424594819545746, "count": 621 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.019652599468827248, "min": -0.10012737661600113, "max": 0.01516697183251381, "count": 621 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.19652599096298218, "min": -1.301655888557434, "max": 0.19717063009738922, "count": 621 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 621 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 621 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.09120000004768372, "min": -0.5394461521735558, "max": 0.319759996732076, "count": 621 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -0.9120000004768372, "min": -8.321600019931793, "max": 4.79639995098114, "count": 621 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.09120000004768372, "min": -0.5394461521735558, "max": 0.319759996732076, "count": 621 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -0.9120000004768372, "min": -8.321600019931793, "max": 4.79639995098114, "count": 621 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 621 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 621 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.014330222292725618, "min": 0.010222057045029941, "max": 0.023527015330425154, "count": 289 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.014330222292725618, "min": 0.010222057045029941, "max": 0.023527015330425154, "count": 289 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0029650022857822477, "min": 1.0000124414470217e-07, "max": 0.005467161916506787, "count": 289 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0029650022857822477, "min": 1.0000124414470217e-07, "max": 0.005467161916506787, "count": 289 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0029783171989644567, "min": 1.0298553796417309e-07, "max": 0.005529568235700329, "count": 289 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0029783171989644567, "min": 1.0298553796417309e-07, "max": 0.005529568235700329, "count": 289 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 289 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 289 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 289 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 289 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 289 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 289 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1719422820", "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\\riywa\\miniconda3\\envs\\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": "2.3.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1719435667" }, "total": 12847.146602499997, "count": 1, "self": 10.015134099987336, "children": { "run_training.setup": { "total": 0.09335929999360815, "count": 1, "self": 0.09335929999360815 }, "TrainerController.start_learning": { "total": 12837.038109100016, "count": 1, "self": 7.793591305642622, "children": { "TrainerController._reset_env": { "total": 8.266323699936038, "count": 31, "self": 8.266323699936038 }, "TrainerController.advance": { "total": 12820.86721929445, "count": 404275, "self": 8.218091678572819, "children": { "env_step": { "total": 5668.175079494191, "count": 404275, "self": 4293.395965773903, "children": { "SubprocessEnvManager._take_step": { "total": 1369.7889026088815, "count": 404275, "self": 44.91610289394157, "children": { "TorchPolicy.evaluate": { "total": 1324.87279971494, "count": 803164, "self": 1324.87279971494 } } }, "workers": { "total": 4.990211111406097, "count": 404274, "self": 0.0, "children": { "worker_root": { "total": 12821.396695613977, "count": 404274, "is_parallel": true, "self": 9497.811211017019, "children": { "steps_from_proto": { "total": 0.04330099999788217, "count": 62, "is_parallel": true, "self": 0.009100599534576759, "children": { "_process_rank_one_or_two_observation": { "total": 0.034200400463305414, "count": 248, "is_parallel": true, "self": 0.034200400463305414 } } }, "UnityEnvironment.step": { "total": 3323.542183596961, "count": 404274, "is_parallel": true, "self": 167.53556519476115, "children": { "UnityEnvironment._generate_step_input": { "total": 145.13486739588552, "count": 404274, "is_parallel": true, "self": 145.13486739588552 }, "communicator.exchange": { "total": 2455.388107987208, "count": 404274, "is_parallel": true, "self": 2455.388107987208 }, "steps_from_proto": { "total": 555.4836430191062, "count": 808548, "is_parallel": true, "self": 115.02406482619699, "children": { "_process_rank_one_or_two_observation": { "total": 440.45957819290925, "count": 3234192, "is_parallel": true, "self": 440.45957819290925 } } } } } } } } } } }, "trainer_advance": { "total": 7144.474048121687, "count": 404274, "self": 61.25754881638568, "children": { "process_trajectory": { "total": 813.1317693050951, "count": 404274, "self": 811.842035805108, "children": { "RLTrainer._checkpoint": { "total": 1.289733499987051, "count": 12, "self": 1.289733499987051 } } }, "_update_policy": { "total": 6270.084730000206, "count": 289, "self": 722.7870975014812, "children": { "TorchPOCAOptimizer.update": { "total": 5547.297632498725, "count": 8670, "self": 5547.297632498725 } } } } } } }, "trainer_threads": { "total": 7.999769877642393e-07, "count": 1, "self": 7.999769877642393e-07 }, "TrainerController._save_models": { "total": 0.11097400001017377, "count": 1, "self": 0.006390900001861155, "children": { "RLTrainer._checkpoint": { "total": 0.10458310000831261, "count": 1, "self": 0.10458310000831261 } } } } } } }