{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.0862834453582764, "min": 2.042527914047241, "max": 3.295727014541626, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 45464.2890625, "min": 14639.1220703125, "max": 124910.296875, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 61.175, "min": 47.26732673267327, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19576.0, "min": 10788.0, "max": 29584.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1505.7816591745682, "min": 1191.0170247988608, "max": 1531.280483098994, "count": 463 }, "SoccerTwos.Self-play.ELO.sum": { "value": 240925.06546793092, "min": 2383.1509562719084, "max": 312178.2458533129, "count": 463 }, "SoccerTwos.Step.mean": { "value": 4999980.0, "min": 9812.0, "max": 4999980.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999980.0, "min": 9812.0, "max": 4999980.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.014435624703764915, "min": -0.07006765156984329, "max": 0.18955844640731812, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -2.3097000122070312, "min": -14.223733901977539, "max": 24.4832706451416, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.017333468422293663, "min": -0.06855880469083786, "max": 0.1912642866373062, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -2.773355007171631, "min": -13.917436599731445, "max": 24.119709014892578, "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": -0.28392124846577643, "min": -0.6385272741317749, "max": 0.4602040855252013, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -45.42739975452423, "min": -58.990400195121765, "max": 49.50580018758774, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.28392124846577643, "min": -0.6385272741317749, "max": 0.4602040855252013, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -45.42739975452423, "min": -58.990400195121765, "max": 49.50580018758774, "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": 0.014146189598250203, "min": 0.010957713452323029, "max": 0.024218131154581594, "count": 237 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.014146189598250203, "min": 0.010957713452323029, "max": 0.024218131154581594, "count": 237 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10090618307391802, "min": 4.4625729666828795e-06, "max": 0.11946777775883674, "count": 237 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10090618307391802, "min": 4.4625729666828795e-06, "max": 0.11946777775883674, "count": 237 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10214464242259662, "min": 4.335292904518913e-06, "max": 0.12197381307681401, "count": 237 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10214464242259662, "min": 4.335292904518913e-06, "max": 0.12197381307681401, "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": "1715894957", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/home/devjwsong/huggingface-deep-rl-unit7/venv/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=../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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1715902739" }, "total": 7781.673325484, "count": 1, "self": 0.2201132559994221, "children": { "run_training.setup": { "total": 0.025726570000017546, "count": 1, "self": 0.025726570000017546 }, "TrainerController.start_learning": { "total": 7781.4274856580005, "count": 1, "self": 4.680679008382867, "children": { "TrainerController._reset_env": { "total": 2.463984238999984, "count": 25, "self": 2.463984238999984 }, "TrainerController.advance": { "total": 7774.1232133696185, "count": 333636, "self": 4.994634041714562, "children": { "env_step": { "total": 6184.973710398018, "count": 333636, "self": 3928.122139760232, "children": { "SubprocessEnvManager._take_step": { "total": 2253.820151919019, "count": 333636, "self": 30.18237176011553, "children": { "TorchPolicy.evaluate": { "total": 2223.6377801589033, "count": 636328, "self": 2223.6377801589033 } } }, "workers": { "total": 3.031418718767071, "count": 333636, "self": 0.0, "children": { "worker_root": { "total": 7769.85643395708, "count": 333636, "is_parallel": true, "self": 4356.037910694045, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0025731679999978496, "count": 2, "is_parallel": true, "self": 0.0011981519999721968, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013750160000256528, "count": 8, "is_parallel": true, "self": 0.0013750160000256528 } } }, "UnityEnvironment.step": { "total": 0.017277346999975407, "count": 1, "is_parallel": true, "self": 0.0003289199999869652, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002797150000048987, "count": 1, "is_parallel": true, "self": 0.0002797150000048987 }, "communicator.exchange": { "total": 0.015655127000002267, "count": 1, "is_parallel": true, "self": 0.015655127000002267 }, "steps_from_proto": { "total": 0.0010135849999812763, "count": 2, "is_parallel": true, "self": 0.0002246819999811578, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007889030000001185, "count": 8, "is_parallel": true, "self": 0.0007889030000001185 } } } } } } }, "UnityEnvironment.step": { "total": 3413.793615476037, "count": 333635, "is_parallel": true, "self": 107.12400640006445, "children": { "UnityEnvironment._generate_step_input": { "total": 64.74492219582334, "count": 333635, "is_parallel": true, "self": 64.74492219582334 }, "communicator.exchange": { "total": 2931.368266230833, "count": 333635, "is_parallel": true, "self": 2931.368266230833 }, "steps_from_proto": { "total": 310.55642064931624, "count": 667270, "is_parallel": true, "self": 65.16929434969228, "children": { "_process_rank_one_or_two_observation": { "total": 245.38712629962396, "count": 2669080, "is_parallel": true, "self": 245.38712629962396 } } } } }, "steps_from_proto": { "total": 0.024907786998596748, "count": 48, "is_parallel": true, "self": 0.005607811002732888, "children": { "_process_rank_one_or_two_observation": { "total": 0.01929997599586386, "count": 192, "is_parallel": true, "self": 0.01929997599586386 } } } } } } } } }, "trainer_advance": { "total": 1584.154868929886, "count": 333636, "self": 39.39380165089369, "children": { "process_trajectory": { "total": 774.8421149559894, "count": 333636, "self": 773.220565004991, "children": { "RLTrainer._checkpoint": { "total": 1.6215499509983147, "count": 10, "self": 1.6215499509983147 } } }, "_update_policy": { "total": 769.9189523230029, "count": 237, "self": 326.89186531397434, "children": { "TorchPOCAOptimizer.update": { "total": 443.0270870090286, "count": 7110, "self": 443.0270870090286 } } } } } } }, "trainer_threads": { "total": 7.239996193675324e-07, "count": 1, "self": 7.239996193675324e-07 }, "TrainerController._save_models": { "total": 0.15960831699976552, "count": 1, "self": 0.0011452509997980087, "children": { "RLTrainer._checkpoint": { "total": 0.1584630659999675, "count": 1, "self": 0.1584630659999675 } } } } } } }