{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.2833622694015503, "min": 1.268653154373169, "max": 3.2956900596618652, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 24558.419921875, "min": 18078.85546875, "max": 139486.09375, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 61.08641975308642, "min": 38.944, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19792.0, "min": 14984.0, "max": 28520.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1716.629988671071, "min": 1173.74448884917, "max": 1767.0185610187846, "count": 4835 }, "SoccerTwos.Self-play.ELO.sum": { "value": 278094.0581647135, "min": 2349.689320532596, "max": 412724.666341037, "count": 4835 }, "SoccerTwos.Step.mean": { "value": 49999962.0, "min": 9276.0, "max": 49999962.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999962.0, "min": 9276.0, "max": 49999962.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.034213077276945114, "min": -0.1459711790084839, "max": 0.18120253086090088, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -5.508305549621582, "min": -29.04826545715332, "max": 22.574892044067383, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.03452947735786438, "min": -0.14649325609207153, "max": 0.17984981834888458, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -5.559245586395264, "min": -29.152158737182617, "max": 22.35865020751953, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.09154410132710238, "min": -0.5332727323878895, "max": 0.4709846175633944, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 14.738600313663483, "min": -73.32240009307861, "max": 70.33040010929108, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.09154410132710238, "min": -0.5332727323878895, "max": 0.4709846175633944, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 14.738600313663483, "min": -73.32240009307861, "max": 70.33040010929108, "count": 5000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01418554427024598, "min": 0.010502571884717326, "max": 0.026226027584198165, "count": 2416 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01418554427024598, "min": 0.010502571884717326, "max": 0.026226027584198165, "count": 2416 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11712498043974241, "min": 4.072932190031982e-08, "max": 0.13310792023936907, "count": 2416 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11712498043974241, "min": 4.072932190031982e-08, "max": 0.13310792023936907, "count": 2416 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11831720819075903, "min": 3.5687613101724006e-08, "max": 0.1363278495768706, "count": 2416 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11831720819075903, "min": 3.5687613101724006e-08, "max": 0.1363278495768706, "count": 2416 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2416 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2416 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2416 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2416 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2416 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2416 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1686598422", "python_version": "3.9.16 (main, Jun 1 2023, 14:10:44) \n[Clang 14.0.3 (clang-1403.0.22.14.1)]", "command_line_arguments": "/Users/lara.thompson/.local/share/virtualenvs/rl-nkqAlb5f/bin/mlagents-learn config/poca/SoccerTwos.yaml --env=training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0", "numpy_version": "1.21.2", "end_time_seconds": "1686813847" }, "total": 197179.864146916, "count": 1, "self": 0.2347347069880925, "children": { "run_training.setup": { "total": 0.015010292000000147, "count": 1, "self": 0.015010292000000147 }, "TrainerController.start_learning": { "total": 197179.614401917, "count": 1, "self": 38.42427379693254, "children": { "TrainerController._reset_env": { "total": 13.669601579106356, "count": 250, "self": 13.669601579106356 }, "TrainerController.advance": { "total": 197127.43439120796, "count": 3435381, "self": 36.20311810952262, "children": { "env_step": { "total": 153058.08845697154, "count": 3435381, "self": 146934.96710122348, "children": { "SubprocessEnvManager._take_step": { "total": 6099.124229360903, "count": 3435381, "self": 173.57608683534454, "children": { "TorchPolicy.evaluate": { "total": 5925.548142525558, "count": 6295672, "self": 5925.548142525558 } } }, "workers": { "total": 23.997126387174493, "count": 3435381, "self": 0.0, "children": { "worker_root": { "total": 197110.10742938519, "count": 3435381, "is_parallel": true, "self": 55221.317502511665, "children": { "steps_from_proto": { "total": 0.3280483091580235, "count": 500, "is_parallel": true, "self": 0.04699413554604703, "children": { "_process_rank_one_or_two_observation": { "total": 0.2810541736119765, "count": 2000, "is_parallel": true, "self": 0.2810541736119765 } } }, "UnityEnvironment.step": { "total": 141888.46187856435, "count": 3435381, "is_parallel": true, "self": 403.6869932109257, "children": { "UnityEnvironment._generate_step_input": { "total": 2255.296417161919, "count": 3435381, "is_parallel": true, "self": 2255.296417161919 }, "communicator.exchange": { "total": 134995.1991358131, "count": 3435381, "is_parallel": true, "self": 134995.1991358131 }, "steps_from_proto": { "total": 4234.279332378406, "count": 6870762, "is_parallel": true, "self": 597.1929536961175, "children": { "_process_rank_one_or_two_observation": { "total": 3637.086378682289, "count": 27483048, "is_parallel": true, "self": 3637.086378682289 } } } } } } } } } } }, "trainer_advance": { "total": 44033.14281612691, "count": 3435381, "self": 292.23401956247835, "children": { "process_trajectory": { "total": 10042.387739908421, "count": 3435381, "self": 10033.98959745048, "children": { "RLTrainer._checkpoint": { "total": 8.398142457941276, "count": 100, "self": 8.398142457941276 } } }, "_update_policy": { "total": 33698.521056656005, "count": 2416, "self": 4746.373526933385, "children": { "TorchPOCAOptimizer.update": { "total": 28952.14752972262, "count": 72480, "self": 28952.14752972262 } } } } } } }, "trainer_threads": { "total": 3.7500285543501377e-07, "count": 1, "self": 3.7500285543501377e-07 }, "TrainerController._save_models": { "total": 0.08613495799363591, "count": 1, "self": 0.002165248995879665, "children": { "RLTrainer._checkpoint": { "total": 0.08396970899775624, "count": 1, "self": 0.08396970899775624 } } } } } } }