{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.3794636726379395, "min": 1.2884377241134644, "max": 3.2957065105438232, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 26971.2734375, "min": 15410.125, "max": 126892.8671875, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 65.13157894736842, "min": 38.6031746031746, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19800.0, "min": 3984.0, "max": 30908.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1742.0551242063318, "min": 1172.5184660541652, "max": 1758.9542390081979, "count": 4912 }, "SoccerTwos.Self-play.ELO.sum": { "value": 264792.3788793624, "min": 2366.814687598051, "max": 437611.8993019908, "count": 4912 }, "SoccerTwos.Step.mean": { "value": 49999978.0, "min": 9796.0, "max": 49999978.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999978.0, "min": 9796.0, "max": 49999978.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.0077554695308208466, "min": -0.1597510129213333, "max": 0.1955847293138504, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 1.1788313388824463, "min": -27.95642852783203, "max": 33.29837417602539, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.006984925363212824, "min": -0.1580408215522766, "max": 0.19503583014011383, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 1.061708688735962, "min": -27.657142639160156, "max": 31.99698257446289, "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": 0.018971052608991925, "min": -0.6153846153846154, "max": 0.38235293416415944, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 2.8835999965667725, "min": -60.80880010128021, "max": 66.13839960098267, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.018971052608991925, "min": -0.6153846153846154, "max": 0.38235293416415944, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 2.8835999965667725, "min": -60.80880010128021, "max": 66.13839960098267, "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": 0.017043410218320787, "min": 0.009336015598576827, "max": 0.02597291834341983, "count": 2421 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017043410218320787, "min": 0.009336015598576827, "max": 0.02597291834341983, "count": 2421 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10036668106913567, "min": 1.550573098067313e-07, "max": 0.12762477546930312, "count": 2421 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10036668106913567, "min": 1.550573098067313e-07, "max": 0.12762477546930312, "count": 2421 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10176810398697853, "min": 1.646743659951729e-07, "max": 0.1294618082543214, "count": 2421 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10176810398697853, "min": 1.646743659951729e-07, "max": 0.1294618082543214, "count": 2421 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2421 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2421 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 2421 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 2421 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2421 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2421 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1701567309", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/home/dfotland/projects/wsl-reinforce/gymnasium-ml-agents/venv-ml-agents/bin/mlagents-learn ./config/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos --run-id=SoccerTwosWSL2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701658081" }, "total": 90771.95874106901, "count": 1, "self": 10.0030337300268, "children": { "run_training.setup": { "total": 0.008348964009201154, "count": 1, "self": 0.008348964009201154 }, "TrainerController.start_learning": { "total": 90761.94735837498, "count": 1, "self": 43.457351466378896, "children": { "TrainerController._reset_env": { "total": 4.1705112889176235, "count": 250, "self": 4.1705112889176235 }, "TrainerController.advance": { "total": 90714.00739625475, "count": 3446828, "self": 44.49552140981541, "children": { "env_step": { "total": 70936.72120019514, "count": 3446828, "self": 34428.18149219357, "children": { "SubprocessEnvManager._take_step": { "total": 36478.73816043974, "count": 3446828, "self": 269.9233846195275, "children": { "TorchPolicy.evaluate": { "total": 36208.81477582021, "count": 6286048, "self": 36208.81477582021 } } }, "workers": { "total": 29.801547561830375, "count": 3446828, "self": 0.0, "children": { "worker_root": { "total": 90679.03026842861, "count": 3446828, "is_parallel": true, "self": 61144.455360339896, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0014958319952711463, "count": 2, "is_parallel": true, "self": 0.00038458796916529536, "children": { "_process_rank_one_or_two_observation": { "total": 0.001111244026105851, "count": 8, "is_parallel": true, "self": 0.001111244026105851 } } }, "UnityEnvironment.step": { "total": 0.0154575560009107, "count": 1, "is_parallel": true, "self": 0.00027115203556604683, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020585799938999116, "count": 1, "is_parallel": true, "self": 0.00020585799938999116 }, "communicator.exchange": { "total": 0.014187530003255233, "count": 1, "is_parallel": true, "self": 0.014187530003255233 }, "steps_from_proto": { "total": 0.0007930159626994282, "count": 2, "is_parallel": true, "self": 0.00016426198999397457, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006287539727054536, "count": 8, "is_parallel": true, "self": 0.0006287539727054536 } } } } } } }, "UnityEnvironment.step": { "total": 29534.345643326495, "count": 3446827, "is_parallel": true, "self": 1003.6647927839076, "children": { "UnityEnvironment._generate_step_input": { "total": 644.072898122773, "count": 3446827, "is_parallel": true, "self": 644.072898122773 }, "communicator.exchange": { "total": 25124.179021216987, "count": 3446827, "is_parallel": true, "self": 25124.179021216987 }, "steps_from_proto": { "total": 2762.428931202827, "count": 6893654, "is_parallel": true, "self": 560.9788271841826, "children": { "_process_rank_one_or_two_observation": { "total": 2201.450104018644, "count": 27574616, "is_parallel": true, "self": 2201.450104018644 } } } } }, "steps_from_proto": { "total": 0.22926476222346537, "count": 498, "is_parallel": true, "self": 0.046726839820621535, "children": { "_process_rank_one_or_two_observation": { "total": 0.18253792240284383, "count": 1992, "is_parallel": true, "self": 0.18253792240284383 } } } } } } } } }, "trainer_advance": { "total": 19732.79067464979, "count": 3446828, "self": 361.4160051846702, "children": { "process_trajectory": { "total": 12432.33903780859, "count": 3446828, "self": 12416.554201690538, "children": { "RLTrainer._checkpoint": { "total": 15.784836118051317, "count": 100, "self": 15.784836118051317 } } }, "_update_policy": { "total": 6939.03563165653, "count": 2421, "self": 3189.62622921844, "children": { "TorchPOCAOptimizer.update": { "total": 3749.40940243809, "count": 72639, "self": 3749.40940243809 } } } } } } }, "trainer_threads": { "total": 4.259636625647545e-07, "count": 1, "self": 4.259636625647545e-07 }, "TrainerController._save_models": { "total": 0.3120989389717579, "count": 1, "self": 0.0008117289980873466, "children": { "RLTrainer._checkpoint": { "total": 0.31128720997367054, "count": 1, "self": 0.31128720997367054 } } } } } } }