{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.4996943473815918, "min": 1.4410089254379272, "max": 3.295714855194092, "count": 3438 }, "SoccerTwos.Policy.Entropy.sum": { "value": 29034.08203125, "min": 16533.53515625, "max": 126133.5078125, "count": 3438 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 55.29213483146067, "min": 40.099173553719005, "max": 999.0, "count": 3438 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19684.0, "min": 16568.0, "max": 23680.0, "count": 3438 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1769.3029567235035, "min": 1199.518796668027, "max": 1786.9354994361488, "count": 2903 }, "SoccerTwos.Self-play.ELO.sum": { "value": 314935.9262967836, "min": 2400.056872686747, "max": 396880.125296206, "count": 2903 }, "SoccerTwos.Step.mean": { "value": 34379957.0, "min": 9420.0, "max": 34379957.0, "count": 3438 }, "SoccerTwos.Step.sum": { "value": 34379957.0, "min": 9420.0, "max": 34379957.0, "count": 3438 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.06473015248775482, "min": -0.13106633722782135, "max": 0.19126904010772705, "count": 3438 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -11.521966934204102, "min": -21.24423599243164, "max": 27.372844696044922, "count": 3438 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.06708361953496933, "min": -0.1304611712694168, "max": 0.18420715630054474, "count": 3438 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -11.940884590148926, "min": -20.94096565246582, "max": 26.564184188842773, "count": 3438 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 3438 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 3438 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.18266516890418663, "min": -0.6985912996789684, "max": 0.40027142422539846, "count": 3438 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -32.51440006494522, "min": -67.31519997119904, "max": 62.060600101947784, "count": 3438 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.18266516890418663, "min": -0.6985912996789684, "max": 0.40027142422539846, "count": 3438 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -32.51440006494522, "min": -67.31519997119904, "max": 62.060600101947784, "count": 3438 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3438 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3438 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016245739072716484, "min": 0.010236145076729979, "max": 0.026171434226368244, "count": 1647 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016245739072716484, "min": 0.010236145076729979, "max": 0.026171434226368244, "count": 1647 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09749607145786285, "min": 1.303780872152771e-09, "max": 0.12087695126732191, "count": 1647 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09749607145786285, "min": 1.303780872152771e-09, "max": 0.12087695126732191, "count": 1647 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09879728729526202, "min": 1.6716754055086843e-09, "max": 0.12250628744562467, "count": 1647 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09879728729526202, "min": 1.6716754055086843e-09, "max": 0.12250628744562467, "count": 1647 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1647 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1647 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 1647 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 1647 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 1647 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 1647 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1687240246", "python_version": "3.9.16 (main, May 15 2023, 23:46:34) \n[GCC 11.2.0]", "command_line_arguments": "/home/gsn/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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.13.1", "numpy_version": "1.21.2", "end_time_seconds": "1687281971" }, "total": 41725.86082921999, "count": 1, "self": 0.15382243998465128, "children": { "run_training.setup": { "total": 0.006956459998036735, "count": 1, "self": 0.006956459998036735 }, "TrainerController.start_learning": { "total": 41725.70005032001, "count": 1, "self": 38.38139236358984, "children": { "TrainerController._reset_env": { "total": 5.89011554485478, "count": 172, "self": 5.89011554485478 }, "TrainerController.advance": { "total": 41681.30991562456, "count": 2332069, "self": 36.7561732805043, "children": { "env_step": { "total": 30310.95269262223, "count": 2332069, "self": 23175.364346630042, "children": { "SubprocessEnvManager._take_step": { "total": 7113.964984677776, "count": 2332069, "self": 251.45113396005763, "children": { "TorchPolicy.evaluate": { "total": 6862.513850717718, "count": 4352586, "self": 6862.513850717718 } } }, "workers": { "total": 21.62336131441407, "count": 2332068, "self": 0.0, "children": { "worker_root": { "total": 41670.77402492873, "count": 2332068, "is_parallel": true, "self": 22827.640426866434, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0013471860002027825, "count": 2, "is_parallel": true, "self": 0.00033335998887196183, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010138260113308206, "count": 8, "is_parallel": true, "self": 0.0010138260113308206 } } }, "UnityEnvironment.step": { "total": 0.01585138399968855, "count": 1, "is_parallel": true, "self": 0.00043924900819547474, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00029077500221319497, "count": 1, "is_parallel": true, "self": 0.00029077500221319497 }, "communicator.exchange": { "total": 0.013881505001336336, "count": 1, "is_parallel": true, "self": 0.013881505001336336 }, "steps_from_proto": { "total": 0.001239854987943545, "count": 2, "is_parallel": true, "self": 0.0004214379732729867, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008184170146705583, "count": 8, "is_parallel": true, "self": 0.0008184170146705583 } } } } } } }, "UnityEnvironment.step": { "total": 18842.932500684517, "count": 2332067, "is_parallel": true, "self": 1005.199737599396, "children": { "UnityEnvironment._generate_step_input": { "total": 653.8556548055931, "count": 2332067, "is_parallel": true, "self": 653.8556548055931 }, "communicator.exchange": { "total": 14294.151582236882, "count": 2332067, "is_parallel": true, "self": 14294.151582236882 }, "steps_from_proto": { "total": 2889.7255260426464, "count": 4664134, "is_parallel": true, "self": 558.2759429966827, "children": { "_process_rank_one_or_two_observation": { "total": 2331.4495830459637, "count": 18656536, "is_parallel": true, "self": 2331.4495830459637 } } } } }, "steps_from_proto": { "total": 0.20109737777966075, "count": 342, "is_parallel": true, "self": 0.04018954404455144, "children": { "_process_rank_one_or_two_observation": { "total": 0.1609078337351093, "count": 1368, "is_parallel": true, "self": 0.1609078337351093 } } } } } } } } }, "trainer_advance": { "total": 11333.601049721823, "count": 2332068, "self": 263.0614240236173, "children": { "process_trajectory": { "total": 3679.7006217081944, "count": 2332068, "self": 3671.9182231991435, "children": { "RLTrainer._checkpoint": { "total": 7.782398509050836, "count": 68, "self": 7.782398509050836 } } }, "_update_policy": { "total": 7390.839003990011, "count": 1647, "self": 4603.101887409488, "children": { "TorchPOCAOptimizer.update": { "total": 2787.7371165805234, "count": 49410, "self": 2787.7371165805234 } } } } } } }, "trainer_threads": { "total": 8.80012521520257e-07, "count": 1, "self": 8.80012521520257e-07 }, "TrainerController._save_models": { "total": 0.11862590699456632, "count": 1, "self": 0.0013739970163442194, "children": { "RLTrainer._checkpoint": { "total": 0.1172519099782221, "count": 1, "self": 0.1172519099782221 } } } } } } }