{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.47501802444458, "min": 1.374983787536621, "max": 3.2957050800323486, "count": 1766 }, "SoccerTwos.Policy.Entropy.sum": { "value": 27942.7421875, "min": 12191.7646484375, "max": 113674.71875, "count": 1766 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 60.49382716049383, "min": 40.644067796610166, "max": 999.0, "count": 1766 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19600.0, "min": 460.0, "max": 31700.0, "count": 1766 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1701.8045556703296, "min": 1199.2507195558546, "max": 1742.0021555293804, "count": 1765 }, "SoccerTwos.Self-play.ELO.sum": { "value": 275692.3380185934, "min": 2398.5014391117093, "max": 396006.93929723254, "count": 1765 }, "SoccerTwos.Step.mean": { "value": 17659974.0, "min": 9866.0, "max": 17659974.0, "count": 1766 }, "SoccerTwos.Step.sum": { "value": 17659974.0, "min": 9866.0, "max": 17659974.0, "count": 1766 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.030388787388801575, "min": -0.1351347714662552, "max": 0.1979745328426361, "count": 1766 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -4.922983646392822, "min": -25.00094985961914, "max": 30.41545295715332, "count": 1766 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.029568247497081757, "min": -0.13394978642463684, "max": 0.20169654488563538, "count": 1766 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -4.790056228637695, "min": -25.035396575927734, "max": 29.17836570739746, "count": 1766 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1766 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1766 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.12718271326135705, "min": -0.6271310366433243, "max": 0.6110352932238111, "count": 1766 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 20.603599548339844, "min": -57.172800064086914, "max": 64.50280028581619, "count": 1766 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.12718271326135705, "min": -0.6271310366433243, "max": 0.6110352932238111, "count": 1766 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 20.603599548339844, "min": -57.172800064086914, "max": 64.50280028581619, "count": 1766 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1766 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1766 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.018386667576851323, "min": 0.009400940702471416, "max": 0.02568165025052925, "count": 855 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018386667576851323, "min": 0.009400940702471416, "max": 0.02568165025052925, "count": 855 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09773399780193964, "min": 0.0008608800346723222, "max": 0.12815671016772587, "count": 855 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09773399780193964, "min": 0.0008608800346723222, "max": 0.12815671016772587, "count": 855 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0995750625928243, "min": 0.0008725534029177983, "max": 0.13050902485847474, "count": 855 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0995750625928243, "min": 0.0008725534029177983, "max": 0.13050902485847474, "count": 855 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 855 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 855 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 855 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 855 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 855 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 855 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1727401939", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/mouse/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env ./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id SoccerTwos --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1727422175" }, "total": 20236.265555019025, "count": 1, "self": 0.06613897858187556, "children": { "run_training.setup": { "total": 0.010145875625312328, "count": 1, "self": 0.010145875625312328 }, "TrainerController.start_learning": { "total": 20236.189270164818, "count": 1, "self": 18.68890165304765, "children": { "TrainerController._reset_env": { "total": 2.2853459110483527, "count": 89, "self": 2.2853459110483527 }, "TrainerController.advance": { "total": 20215.063338052947, "count": 1216889, "self": 17.187379616778344, "children": { "env_step": { "total": 14578.162566474173, "count": 1216889, "self": 9343.769771191757, "children": { "SubprocessEnvManager._take_step": { "total": 5223.490688921418, "count": 1216889, "self": 93.50209888070822, "children": { "TorchPolicy.evaluate": { "total": 5129.98859004071, "count": 2219796, "self": 5129.98859004071 } } }, "workers": { "total": 10.902106360998005, "count": 1216888, "self": 0.0, "children": { "worker_root": { "total": 20214.881564092357, "count": 1216888, "is_parallel": true, "self": 12771.828260323498, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017272476106882095, "count": 2, "is_parallel": true, "self": 0.0006416612304747105, "children": { "_process_rank_one_or_two_observation": { "total": 0.001085586380213499, "count": 8, "is_parallel": true, "self": 0.001085586380213499 } } }, "UnityEnvironment.step": { "total": 0.015516959130764008, "count": 1, "is_parallel": true, "self": 0.00034855399280786514, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003095269203186035, "count": 1, "is_parallel": true, "self": 0.0003095269203186035 }, "communicator.exchange": { "total": 0.013750093057751656, "count": 1, "is_parallel": true, "self": 0.013750093057751656 }, "steps_from_proto": { "total": 0.0011087851598858833, "count": 2, "is_parallel": true, "self": 0.0002498747780919075, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008589103817939758, "count": 8, "is_parallel": true, "self": 0.0008589103817939758 } } } } } } }, "UnityEnvironment.step": { "total": 7442.946317696478, "count": 1216887, "is_parallel": true, "self": 401.9487909353338, "children": { "UnityEnvironment._generate_step_input": { "total": 304.60035434551537, "count": 1216887, "is_parallel": true, "self": 304.60035434551537 }, "communicator.exchange": { "total": 5515.571368062869, "count": 1216887, "is_parallel": true, "self": 5515.571368062869 }, "steps_from_proto": { "total": 1220.8258043527603, "count": 2433774, "is_parallel": true, "self": 262.87593224598095, "children": { "_process_rank_one_or_two_observation": { "total": 957.9498721067794, "count": 9735096, "is_parallel": true, "self": 957.9498721067794 } } } } }, "steps_from_proto": { "total": 0.10698607238009572, "count": 176, "is_parallel": true, "self": 0.02309997845441103, "children": { "_process_rank_one_or_two_observation": { "total": 0.08388609392568469, "count": 704, "is_parallel": true, "self": 0.08388609392568469 } } } } } } } } }, "trainer_advance": { "total": 5619.7133919619955, "count": 1216888, "self": 129.13575205672532, "children": { "process_trajectory": { "total": 2687.910498926416, "count": 1216888, "self": 2682.941142951604, "children": { "RLTrainer._checkpoint": { "total": 4.969355974812061, "count": 35, "self": 4.969355974812061 } } }, "_update_policy": { "total": 2802.667140978854, "count": 855, "self": 1491.3160019135103, "children": { "TorchPOCAOptimizer.update": { "total": 1311.351139065344, "count": 25665, "self": 1311.351139065344 } } } } } } }, "trainer_threads": { "total": 5.918554961681366e-07, "count": 1, "self": 5.918554961681366e-07 }, "TrainerController._save_models": { "total": 0.15168395591899753, "count": 1, "self": 0.0008070687763392925, "children": { "RLTrainer._checkpoint": { "total": 0.15087688714265823, "count": 1, "self": 0.15087688714265823 } } } } } } }