{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.503404140472412, "min": 2.4523873329162598, "max": 2.5370821952819824, "count": 37 }, "SoccerTwos.Policy.Entropy.sum": { "value": 47905.140625, "min": 16055.9697265625, "max": 55159.47265625, "count": 37 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 64.93333333333334, "min": 49.91752577319588, "max": 76.84375, "count": 37 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19480.0, "min": 4772.0, "max": 20184.0, "count": 37 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1652.4748588887048, "min": 1642.8951631352754, "max": 1669.7917318437467, "count": 37 }, "SoccerTwos.Self-play.ELO.sum": { "value": 247871.2288333057, "min": 76077.51671093542, "max": 321056.13316160464, "count": 37 }, "SoccerTwos.Step.mean": { "value": 6549982.0, "min": 6189948.0, "max": 6549982.0, "count": 37 }, "SoccerTwos.Step.sum": { "value": 6549982.0, "min": 6189948.0, "max": 6549982.0, "count": 37 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.051142871379852295, "min": -0.06000871956348419, "max": 0.0756918340921402, "count": 37 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 7.671430587768555, "min": -9.386945724487305, "max": 12.262077331542969, "count": 37 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.05099420249462128, "min": -0.05922776460647583, "max": 0.07353535294532776, "count": 37 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 7.649130344390869, "min": -9.559730529785156, "max": 11.912727355957031, "count": 37 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 37 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 37 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.07690666834513346, "min": -0.2579976199638276, "max": 0.22876027267273158, "count": 37 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 11.53600025177002, "min": -43.343600153923035, "max": 35.7960000038147, "count": 37 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.07690666834513346, "min": -0.2579976199638276, "max": 0.22876027267273158, "count": 37 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 11.53600025177002, "min": -43.343600153923035, "max": 35.7960000038147, "count": 37 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 37 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 37 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.013742929190630093, "min": 0.013162332853729216, "max": 0.021872061599666873, "count": 17 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.013742929190630093, "min": 0.013162332853729216, "max": 0.021872061599666873, "count": 17 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.060539432987570765, "min": 0.05456341157356898, "max": 0.06828681615491708, "count": 17 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.060539432987570765, "min": 0.05456341157356898, "max": 0.06828681615491708, "count": 17 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.06114285662770271, "min": 0.05531582894424598, "max": 0.0692600845048825, "count": 17 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.06114285662770271, "min": 0.05531582894424598, "max": 0.0692600845048825, "count": 17 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.00025000000000000006, "min": 0.00025000000000000006, "max": 0.00025000000000000006, "count": 17 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.00025000000000000006, "min": 0.00025000000000000006, "max": 0.00025000000000000006, "count": 17 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.25, "min": 0.25, "max": 0.25, "count": 17 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.25, "min": 0.25, "max": 0.25, "count": 17 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.010000000000000002, "min": 0.010000000000000002, "max": 0.010000000000000002, "count": 17 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.010000000000000002, "min": 0.010000000000000002, "max": 0.010000000000000002, "count": 17 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1683487709", "python_version": "3.9.16 | packaged by conda-forge | (main, Feb 1 2023, 21:38:11) \n[Clang 14.0.6 ]", "command_line_arguments": "/Users/andreas.bjarlestam/mambaforge/envs/huggingface-rl-course/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0", "numpy_version": "1.21.2", "end_time_seconds": "1683489353" }, "total": 1643.169040458, "count": 1, "self": 0.11722787500002596, "children": { "run_training.setup": { "total": 0.013663792000000008, "count": 1, "self": 0.013663792000000008 }, "TrainerController.start_learning": { "total": 1643.038148791, "count": 1, "self": 0.31101058200579246, "children": { "TrainerController._reset_env": { "total": 2.2248240839999744, "count": 3, "self": 2.2248240839999744 }, "TrainerController.advance": { "total": 1640.320858083994, "count": 25389, "self": 0.2661743909673078, "children": { "env_step": { "total": 1330.830156340017, "count": 25389, "self": 1284.3852757490256, "children": { "SubprocessEnvManager._take_step": { "total": 46.23812745699054, "count": 25389, "self": 1.2487462569900671, "children": { "TorchPolicy.evaluate": { "total": 44.98938120000047, "count": 46132, "self": 44.98938120000047 } } }, "workers": { "total": 0.20675313400085837, "count": 25388, "self": 0.0, "children": { "worker_root": { "total": 1640.2869981199963, "count": 25388, "is_parallel": true, "self": 393.89563319499894, "children": { "steps_from_proto": { "total": 0.005132874999992598, "count": 6, "is_parallel": true, "self": 0.0006161679999161507, "children": { "_process_rank_one_or_two_observation": { "total": 0.0045167070000764475, "count": 24, "is_parallel": true, "self": 0.0045167070000764475 } } }, "UnityEnvironment.step": { "total": 1246.3862320499973, "count": 25388, "is_parallel": true, "self": 3.1823133230072926, "children": { "UnityEnvironment._generate_step_input": { "total": 22.304695663003482, "count": 25388, "is_parallel": true, "self": 22.304695663003482 }, "communicator.exchange": { "total": 1175.0904308869885, "count": 25388, "is_parallel": true, "self": 1175.0904308869885 }, "steps_from_proto": { "total": 45.808792176997834, "count": 50776, "is_parallel": true, "self": 5.091343413956125, "children": { "_process_rank_one_or_two_observation": { "total": 40.71744876304171, "count": 203104, "is_parallel": true, "self": 40.71744876304171 } } } } } } } } } } }, "trainer_advance": { "total": 309.2245273530094, "count": 25388, "self": 2.159055672025943, "children": { "process_trajectory": { "total": 68.22423439098337, "count": 25388, "self": 68.22423439098337 }, "_update_policy": { "total": 238.8412372900001, "count": 17, "self": 29.788104290999627, "children": { "TorchPOCAOptimizer.update": { "total": 209.05313299900047, "count": 510, "self": 209.05313299900047 } } } } } } }, "trainer_threads": { "total": 4.1600014810683206e-07, "count": 1, "self": 4.1600014810683206e-07 }, "TrainerController._save_models": { "total": 0.18145562500012602, "count": 1, "self": 0.0011100420001639577, "children": { "RLTrainer._checkpoint": { "total": 0.18034558299996206, "count": 1, "self": 0.18034558299996206 } } } } } } }