{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.897310256958008, "min": 2.848477363586426, "max": 3.295743465423584, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 40701.4140625, "min": 13514.955078125, "max": 119905.03125, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 999.0, "min": 449.1, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19980.0, "min": 10852.0, "max": 29248.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1202.0664214104136, "min": 1197.0971271610715, "max": 1214.2053557656131, "count": 240 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2404.132842820827, "min": 2394.194254322143, "max": 16819.672321847218, "count": 240 }, "SoccerTwos.Step.mean": { "value": 4999266.0, "min": 9356.0, "max": 4999266.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999266.0, "min": 9356.0, "max": 4999266.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.00028921442572027445, "min": -0.021255120635032654, "max": 0.01638713665306568, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.0028921442572027445, "min": -0.22371436655521393, "max": 0.16416141390800476, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.00027330080047249794, "min": -0.026361608877778053, "max": 0.01724361814558506, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.0027330080047249794, "min": -0.26361608505249023, "max": 0.1724361777305603, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0, "min": -0.6363636363636364, "max": 0.28514666159947716, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.0, "min": -8.0, "max": 4.277199923992157, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0, "min": -0.6363636363636364, "max": 0.28514666159947716, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.0, "min": -8.0, "max": 4.277199923992157, "count": 500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.012303747368666034, "min": 0.01181834559198857, "max": 0.02552387221949175, "count": 231 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.012303747368666034, "min": 0.01181834559198857, "max": 0.02552387221949175, "count": 231 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 8.162543826036502e-08, "min": 3.870426934504678e-09, "max": 0.005837825002769629, "count": 231 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 8.162543826036502e-08, "min": 3.870426934504678e-09, "max": 0.005837825002769629, "count": 231 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 7.314902236525238e-08, "min": 3.573569388552282e-09, "max": 0.005854411035155257, "count": 231 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 7.314902236525238e-08, "min": 3.573569388552282e-09, "max": 0.005854411035155257, "count": 231 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 231 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 231 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 231 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 231 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 231 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 231 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1686084129", "python_version": "3.9.16 (main, Mar 8 2023, 04:29:44) \n[Clang 14.0.6 ]", "command_line_arguments": "/Users/pete/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --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", "numpy_version": "1.21.2", "end_time_seconds": "1686106843" }, "total": 22712.8804085, "count": 1, "self": 2.4257677500027057, "children": { "run_training.setup": { "total": 0.033340499999999995, "count": 1, "self": 0.033340499999999995 }, "TrainerController.start_learning": { "total": 22710.42130025, "count": 1, "self": 4.830903147627396, "children": { "TrainerController._reset_env": { "total": 5.326529873997477, "count": 25, "self": 5.326529873997477 }, "TrainerController.advance": { "total": 22700.152816895377, "count": 324961, "self": 4.345810035294562, "children": { "env_step": { "total": 4773.947685887066, "count": 324961, "self": 3821.429469863415, "children": { "SubprocessEnvManager._take_step": { "total": 949.2356304140326, "count": 324961, "self": 25.590473819653198, "children": { "TorchPolicy.evaluate": { "total": 923.6451565943794, "count": 645372, "self": 923.6451565943794 } } }, "workers": { "total": 3.2825856096184918, "count": 324961, "self": 0.0, "children": { "worker_root": { "total": 22698.56535456274, "count": 324961, "is_parallel": true, "self": 19473.169866872755, "children": { "steps_from_proto": { "total": 0.03979620699360531, "count": 50, "is_parallel": true, "self": 0.007292419975294173, "children": { "_process_rank_one_or_two_observation": { "total": 0.03250378701831114, "count": 200, "is_parallel": true, "self": 0.03250378701831114 } } }, "UnityEnvironment.step": { "total": 3225.3556914829906, "count": 324961, "is_parallel": true, "self": 142.27648066783104, "children": { "UnityEnvironment._generate_step_input": { "total": 96.10931491563395, "count": 324961, "is_parallel": true, "self": 96.10931491563395 }, "communicator.exchange": { "total": 2528.892965574136, "count": 324961, "is_parallel": true, "self": 2528.892965574136 }, "steps_from_proto": { "total": 458.0769303253895, "count": 649922, "is_parallel": true, "self": 74.26221355696799, "children": { "_process_rank_one_or_two_observation": { "total": 383.81471676842153, "count": 2599688, "is_parallel": true, "self": 383.81471676842153 } } } } } } } } } } }, "trainer_advance": { "total": 17921.859320973017, "count": 324961, "self": 59.730450604132784, "children": { "process_trajectory": { "total": 1957.5087623638713, "count": 324961, "self": 1954.081727070871, "children": { "RLTrainer._checkpoint": { "total": 3.4270352930002446, "count": 10, "self": 3.4270352930002446 } } }, "_update_policy": { "total": 15904.620108005014, "count": 231, "self": 683.2543208339684, "children": { "TorchPOCAOptimizer.update": { "total": 15221.365787171046, "count": 6936, "self": 15221.365787171046 } } } } } } }, "trainer_threads": { "total": 6.249974831007421e-07, "count": 1, "self": 6.249974831007421e-07 }, "TrainerController._save_models": { "total": 0.11104970800079172, "count": 1, "self": 0.003987708001659485, "children": { "RLTrainer._checkpoint": { "total": 0.10706199999913224, "count": 1, "self": 0.10706199999913224 } } } } } } }