{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.9442510604858398, "min": 1.9251229763031006, "max": 3.2957751750946045, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 38013.99609375, "min": 28760.005859375, "max": 117699.8515625, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 49.83, "min": 40.16528925619835, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19932.0, "min": 11668.0, "max": 30992.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1503.2260117014357, "min": 1198.7234718671002, "max": 1519.056163524618, "count": 470 }, "SoccerTwos.Self-play.ELO.sum": { "value": 300645.20234028716, "min": 2397.4469437342004, "max": 358067.5392072537, "count": 470 }, "SoccerTwos.Step.mean": { "value": 4999990.0, "min": 9514.0, "max": 4999990.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999990.0, "min": 9514.0, "max": 4999990.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.015706663951277733, "min": -0.0942673608660698, "max": 0.14426925778388977, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 3.1256260871887207, "min": -16.119718551635742, "max": 24.510446548461914, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.013603504747152328, "min": -0.0953456461429596, "max": 0.1495077759027481, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 2.7070975303649902, "min": -16.304105758666992, "max": 24.941312789916992, "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": -0.011024119865954222, "min": -0.6497999990687651, "max": 0.37245106443445736, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -2.19379985332489, "min": -54.325600028038025, "max": 65.07360023260117, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.011024119865954222, "min": -0.6497999990687651, "max": 0.37245106443445736, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -2.19379985332489, "min": -54.325600028038025, "max": 65.07360023260117, "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": 0.018317764533761268, "min": 0.010698239152164508, "max": 0.0232989558018744, "count": 239 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018317764533761268, "min": 0.010698239152164508, "max": 0.0232989558018744, "count": 239 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11499877870082856, "min": 2.458588736165742e-05, "max": 0.1263156647483508, "count": 239 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11499877870082856, "min": 2.458588736165742e-05, "max": 0.1263156647483508, "count": 239 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11676812221606572, "min": 2.4948281437294404e-05, "max": 0.12844556644558908, "count": 239 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11676812221606572, "min": 2.4948281437294404e-05, "max": 0.12844556644558908, "count": 239 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 239 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 239 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 239 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 239 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 239 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 239 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1707614940", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/victor/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --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": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1707627707" }, "total": 12766.547348516993, "count": 1, "self": 0.32042913197074085, "children": { "run_training.setup": { "total": 0.01880163702298887, "count": 1, "self": 0.01880163702298887 }, "TrainerController.start_learning": { "total": 12766.208117748, "count": 1, "self": 5.962926205189433, "children": { "TrainerController._reset_env": { "total": 2.66041523302556, "count": 25, "self": 2.66041523302556 }, "TrainerController.advance": { "total": 12757.38144438478, "count": 338538, "self": 6.1658543918747455, "children": { "env_step": { "total": 4587.873034044984, "count": 338538, "self": 3592.0257112507825, "children": { "SubprocessEnvManager._take_step": { "total": 991.9554720758752, "count": 338538, "self": 36.427117089449894, "children": { "TorchPolicy.evaluate": { "total": 955.5283549864253, "count": 633286, "self": 955.5283549864253 } } }, "workers": { "total": 3.891850718326168, "count": 338538, "self": 0.0, "children": { "worker_root": { "total": 12756.9396989425, "count": 338538, "is_parallel": true, "self": 9884.010677731188, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003197050013113767, "count": 2, "is_parallel": true, "self": 0.0015253629826474935, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016716870304662734, "count": 8, "is_parallel": true, "self": 0.0016716870304662734 } } }, "UnityEnvironment.step": { "total": 0.027346729999408126, "count": 1, "is_parallel": true, "self": 0.0005745459930039942, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003659430076368153, "count": 1, "is_parallel": true, "self": 0.0003659430076368153 }, "communicator.exchange": { "total": 0.024912182008847594, "count": 1, "is_parallel": true, "self": 0.024912182008847594 }, "steps_from_proto": { "total": 0.001494058989919722, "count": 2, "is_parallel": true, "self": 0.0003006889601238072, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011933700297959149, "count": 8, "is_parallel": true, "self": 0.0011933700297959149 } } } } } } }, "UnityEnvironment.step": { "total": 2872.8941820973996, "count": 338537, "is_parallel": true, "self": 171.00910928664962, "children": { "UnityEnvironment._generate_step_input": { "total": 121.2719798910548, "count": 338537, "is_parallel": true, "self": 121.2719798910548 }, "communicator.exchange": { "total": 2083.245992752578, "count": 338537, "is_parallel": true, "self": 2083.245992752578 }, "steps_from_proto": { "total": 497.3671001671173, "count": 677074, "is_parallel": true, "self": 96.80499770634924, "children": { "_process_rank_one_or_two_observation": { "total": 400.5621024607681, "count": 2708296, "is_parallel": true, "self": 400.5621024607681 } } } } }, "steps_from_proto": { "total": 0.034839113912312314, "count": 48, "is_parallel": true, "self": 0.006737367890309542, "children": { "_process_rank_one_or_two_observation": { "total": 0.02810174602200277, "count": 192, "is_parallel": true, "self": 0.02810174602200277 } } } } } } } } }, "trainer_advance": { "total": 8163.342555947922, "count": 338538, "self": 46.3605592820968, "children": { "process_trajectory": { "total": 1028.2696332178602, "count": 338538, "self": 1024.4807991608395, "children": { "RLTrainer._checkpoint": { "total": 3.788834057020722, "count": 10, "self": 3.788834057020722 } } }, "_update_policy": { "total": 7088.712363447965, "count": 239, "self": 521.196462993772, "children": { "TorchPOCAOptimizer.update": { "total": 6567.515900454193, "count": 7173, "self": 6567.515900454193 } } } } } } }, "trainer_threads": { "total": 6.539921741932631e-07, "count": 1, "self": 6.539921741932631e-07 }, "TrainerController._save_models": { "total": 0.203331271011848, "count": 1, "self": 0.001419581996742636, "children": { "RLTrainer._checkpoint": { "total": 0.20191168901510537, "count": 1, "self": 0.20191168901510537 } } } } } } }