{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.6801722049713135, "min": 1.6689929962158203, "max": 3.295753240585327, "count": 522 }, "SoccerTwos.Policy.Entropy.sum": { "value": 31345.29296875, "min": 16059.88671875, "max": 117480.875, "count": 522 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 47.85436893203884, "min": 37.19402985074627, "max": 999.0, "count": 522 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19716.0, "min": 12776.0, "max": 28128.0, "count": 522 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1512.3841506926258, "min": 1182.721040420331, "max": 1520.1387888025301, "count": 500 }, "SoccerTwos.Self-play.ELO.sum": { "value": 311551.1350426809, "min": 2365.575166765614, "max": 402909.03120493336, "count": 500 }, "SoccerTwos.Step.mean": { "value": 5219984.0, "min": 9082.0, "max": 5219984.0, "count": 522 }, "SoccerTwos.Step.sum": { "value": 5219984.0, "min": 9082.0, "max": 5219984.0, "count": 522 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.017524413764476776, "min": -0.12234243750572205, "max": 0.30277761816978455, "count": 522 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -3.5925049781799316, "min": -24.590829849243164, "max": 32.93498611450195, "count": 522 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.01664070226252079, "min": -0.12715943157672882, "max": 0.2870791554450989, "count": 522 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -3.411344051361084, "min": -25.559045791625977, "max": 31.987327575683594, "count": 522 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 522 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 522 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.1805639040179369, "min": -0.5964551711904591, "max": 0.48996875062584877, "count": 522 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -37.01560032367706, "min": -56.88379991054535, "max": 51.32639992237091, "count": 522 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.1805639040179369, "min": -0.5964551711904591, "max": 0.48996875062584877, "count": 522 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -37.01560032367706, "min": -56.88379991054535, "max": 51.32639992237091, "count": 522 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 522 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 522 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016975674087492128, "min": 0.011308841101708822, "max": 0.024441575802241763, "count": 250 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016975674087492128, "min": 0.011308841101708822, "max": 0.024441575802241763, "count": 250 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09598184923330942, "min": 1.3440602704880196e-06, "max": 0.10366184016068776, "count": 250 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09598184923330942, "min": 1.3440602704880196e-06, "max": 0.10366184016068776, "count": 250 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09921732048193614, "min": 4.471496655848265e-06, "max": 0.10685077408949534, "count": 250 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09921732048193614, "min": 4.471496655848265e-06, "max": 0.10685077408949534, "count": 250 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0005000000000000001, "min": 0.0005000000000000001, "max": 0.0005000000000000001, "count": 250 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0005000000000000001, "min": 0.0005000000000000001, "max": 0.0005000000000000001, "count": 250 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 250 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 250 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 250 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 250 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1692717082", "python_version": "3.9.17 (main, Jul 5 2023, 20:41:20) \n[GCC 11.2.0]", "command_line_arguments": "/home/genis/miniconda3/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": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1692734710" }, "total": 17627.666772411998, "count": 1, "self": 0.09028954200039152, "children": { "run_training.setup": { "total": 0.008287695000035455, "count": 1, "self": 0.008287695000035455 }, "TrainerController.start_learning": { "total": 17627.568195174998, "count": 1, "self": 7.836454700638569, "children": { "TrainerController._reset_env": { "total": 2.0494618500052866, "count": 21, "self": 2.0494618500052866 }, "TrainerController.advance": { "total": 17617.451557357355, "count": 355657, "self": 7.943129163682897, "children": { "env_step": { "total": 5259.7881734208, "count": 355657, "self": 4268.029192443379, "children": { "SubprocessEnvManager._take_step": { "total": 987.002381628069, "count": 355657, "self": 38.885623749441834, "children": { "TorchPolicy.evaluate": { "total": 948.1167578786271, "count": 659920, "self": 948.1167578786271 } } }, "workers": { "total": 4.756599349352882, "count": 355656, "self": 0.0, "children": { "worker_root": { "total": 17616.246501720587, "count": 355656, "is_parallel": true, "self": 14199.876406307758, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002839553000058004, "count": 2, "is_parallel": true, "self": 0.0013376410003047567, "children": { "_process_rank_one_or_two_observation": { "total": 0.001501911999753247, "count": 8, "is_parallel": true, "self": 0.001501911999753247 } } }, "UnityEnvironment.step": { "total": 0.019501769000044078, "count": 1, "is_parallel": true, "self": 0.00047463800001423806, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00035923199993703747, "count": 1, "is_parallel": true, "self": 0.00035923199993703747 }, "communicator.exchange": { "total": 0.017162689000087994, "count": 1, "is_parallel": true, "self": 0.017162689000087994 }, "steps_from_proto": { "total": 0.0015052100000048085, "count": 2, "is_parallel": true, "self": 0.00028915600000800623, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012160539999968023, "count": 8, "is_parallel": true, "self": 0.0012160539999968023 } } } } } } }, "UnityEnvironment.step": { "total": 3416.3324846668224, "count": 355655, "is_parallel": true, "self": 192.92021787136537, "children": { "UnityEnvironment._generate_step_input": { "total": 129.56033859774914, "count": 355655, "is_parallel": true, "self": 129.56033859774914 }, "communicator.exchange": { "total": 2474.453554164158, "count": 355655, "is_parallel": true, "self": 2474.453554164158 }, "steps_from_proto": { "total": 619.3983740335495, "count": 711310, "is_parallel": true, "self": 122.86005064013443, "children": { "_process_rank_one_or_two_observation": { "total": 496.5383233934151, "count": 2845240, "is_parallel": true, "self": 496.5383233934151 } } } } }, "steps_from_proto": { "total": 0.03761074600720349, "count": 40, "is_parallel": true, "self": 0.0073545120210383175, "children": { "_process_rank_one_or_two_observation": { "total": 0.03025623398616517, "count": 160, "is_parallel": true, "self": 0.03025623398616517 } } } } } } } } }, "trainer_advance": { "total": 12349.720254772872, "count": 355656, "self": 53.74877238922272, "children": { "process_trajectory": { "total": 1201.6411975316382, "count": 355656, "self": 1198.943791865635, "children": { "RLTrainer._checkpoint": { "total": 2.6974056660033057, "count": 10, "self": 2.6974056660033057 } } }, "_update_policy": { "total": 11094.33028485201, "count": 251, "self": 778.9787935760087, "children": { "TorchPOCAOptimizer.update": { "total": 10315.351491276002, "count": 7530, "self": 10315.351491276002 } } } } } } }, "trainer_threads": { "total": 1.0909971024375409e-06, "count": 1, "self": 1.0909971024375409e-06 }, "TrainerController._save_models": { "total": 0.23072017600134131, "count": 1, "self": 0.0015350430003309157, "children": { "RLTrainer._checkpoint": { "total": 0.2291851330010104, "count": 1, "self": 0.2291851330010104 } } } } } } }