{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.508293628692627, "min": 1.3688874244689941, "max": 3.295727014541626, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 30889.853515625, "min": 11488.4580078125, "max": 140567.859375, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 69.91428571428571, "min": 45.416666666666664, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19576.0, "min": 13892.0, "max": 26368.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1716.024068310473, "min": 1180.2819151877213, "max": 1740.170459435458, "count": 4231 }, "SoccerTwos.Self-play.ELO.sum": { "value": 240243.36956346623, "min": 2360.613902997477, "max": 365188.9635329818, "count": 4231 }, "SoccerTwos.Step.mean": { "value": 49999852.0, "min": 9200.0, "max": 49999852.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999852.0, "min": 9200.0, "max": 49999852.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.029648413881659508, "min": -0.13339951634407043, "max": 0.16061967611312866, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -4.150777816772461, "min": -22.645069122314453, "max": 23.129234313964844, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.029943576082587242, "min": -0.13491928577423096, "max": 0.15439139306545258, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -4.192100524902344, "min": -22.547657012939453, "max": 22.23236083984375, "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": 0.06587428535733904, "min": -0.6666666666666666, "max": 0.5155545373404906, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 9.222399950027466, "min": -66.96560001373291, "max": 55.16959989070892, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.06587428535733904, "min": -0.6666666666666666, "max": 0.5155545373404906, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 9.222399950027466, "min": -66.96560001373291, "max": 55.16959989070892, "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": 0.01592964834611242, "min": 0.010079040457882608, "max": 0.026032148901140317, "count": 2395 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01592964834611242, "min": 0.010079040457882608, "max": 0.026032148901140317, "count": 2395 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09858209987481435, "min": 4.718942782829435e-10, "max": 0.12129973868529002, "count": 2395 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09858209987481435, "min": 4.718942782829435e-10, "max": 0.12129973868529002, "count": 2395 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09946659977237383, "min": 4.833817466668814e-10, "max": 0.12360452065865199, "count": 2395 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09946659977237383, "min": 4.833817466668814e-10, "max": 0.12360452065865199, "count": 2395 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2395 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2395 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 2395 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 2395 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 2395 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 2395 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1734646845", "python_version": "3.10.12 (main, Dec 19 2024, 13:45:53) [GCC 13.3.0]", "command_line_arguments": "/home/bbian/.pyenv/versions/venv_unit7/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./SoccerTwos.x86_64 --run-id=SoccerTwos-bbian --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1734817370" }, "total": 170705.52215281792, "count": 1, "self": 0.32216454099398106, "children": { "run_training.setup": { "total": 0.016590273939073086, "count": 1, "self": 0.016590273939073086 }, "TrainerController.start_learning": { "total": 170705.183398003, "count": 1, "self": 74.26048158481717, "children": { "TrainerController._reset_env": { "total": 12.931219580350444, "count": 250, "self": 12.931219580350444 }, "TrainerController.advance": { "total": 170617.8357798258, "count": 3386722, "self": 74.21399708266836, "children": { "env_step": { "total": 94585.30471019982, "count": 3386722, "self": 82461.74639354029, "children": { "SubprocessEnvManager._take_step": { "total": 12080.145025142585, "count": 3386722, "self": 495.9865917117568, "children": { "TorchPolicy.evaluate": { "total": 11584.158433430828, "count": 6321222, "self": 11584.158433430828 } } }, "workers": { "total": 43.41329151694663, "count": 3386722, "self": 0.0, "children": { "worker_root": { "total": 170550.2573246971, "count": 3386722, "is_parallel": true, "self": 98676.26697820507, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0066442720126360655, "count": 2, "is_parallel": true, "self": 0.0014839951181784272, "children": { "_process_rank_one_or_two_observation": { "total": 0.005160276894457638, "count": 8, "is_parallel": true, "self": 0.005160276894457638 } } }, "UnityEnvironment.step": { "total": 0.04355000297073275, "count": 1, "is_parallel": true, "self": 0.0009142749477177858, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0010049419943243265, "count": 1, "is_parallel": true, "self": 0.0010049419943243265 }, "communicator.exchange": { "total": 0.03873727994505316, "count": 1, "is_parallel": true, "self": 0.03873727994505316 }, "steps_from_proto": { "total": 0.002893506083637476, "count": 2, "is_parallel": true, "self": 0.0005713241407647729, "children": { "_process_rank_one_or_two_observation": { "total": 0.002322181942872703, "count": 8, "is_parallel": true, "self": 0.002322181942872703 } } } } } } }, "UnityEnvironment.step": { "total": 71873.0294233181, "count": 3386721, "is_parallel": true, "self": 3845.6331649579806, "children": { "UnityEnvironment._generate_step_input": { "total": 3156.2233795622597, "count": 3386721, "is_parallel": true, "self": 3156.2233795622597 }, "communicator.exchange": { "total": 52766.77928065765, "count": 3386721, "is_parallel": true, "self": 52766.77928065765 }, "steps_from_proto": { "total": 12104.393598140217, "count": 6773442, "is_parallel": true, "self": 2274.7435706499964, "children": { "_process_rank_one_or_two_observation": { "total": 9829.650027490221, "count": 27093768, "is_parallel": true, "self": 9829.650027490221 } } } } }, "steps_from_proto": { "total": 0.960923173930496, "count": 498, "is_parallel": true, "self": 0.18147785926703364, "children": { "_process_rank_one_or_two_observation": { "total": 0.7794453146634623, "count": 1992, "is_parallel": true, "self": 0.7794453146634623 } } } } } } } } }, "trainer_advance": { "total": 75958.31707254332, "count": 3386722, "self": 572.0106428153813, "children": { "process_trajectory": { "total": 9398.698220963008, "count": 3386722, "self": 9381.037947491044, "children": { "RLTrainer._checkpoint": { "total": 17.660273471963592, "count": 100, "self": 17.660273471963592 } } }, "_update_policy": { "total": 65987.60820876493, "count": 2395, "self": 6989.456282100524, "children": { "TorchPOCAOptimizer.update": { "total": 58998.1519266644, "count": 71862, "self": 58998.1519266644 } } } } } } }, "trainer_threads": { "total": 8.600763976573944e-07, "count": 1, "self": 8.600763976573944e-07 }, "TrainerController._save_models": { "total": 0.15591615193989128, "count": 1, "self": 0.001197621924802661, "children": { "RLTrainer._checkpoint": { "total": 0.15471853001508862, "count": 1, "self": 0.15471853001508862 } } } } } } }