{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.603534460067749, "min": 1.5445671081542969, "max": 3.2957382202148438, "count": 1117 }, "SoccerTwos.Policy.Entropy.sum": { "value": 31557.55859375, "min": 25951.4296875, "max": 128153.71875, "count": 1117 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 41.6578947368421, "min": 37.34615384615385, "max": 999.0, "count": 1117 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 18996.0, "min": 14572.0, "max": 27108.0, "count": 1117 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1592.5233640684746, "min": 1197.7046097348552, "max": 1610.753297285041, "count": 1089 }, "SoccerTwos.Self-play.ELO.sum": { "value": 363095.3270076122, "min": 2395.4092194697105, "max": 415747.5658378394, "count": 1089 }, "SoccerTwos.Step.mean": { "value": 11169974.0, "min": 9570.0, "max": 11169974.0, "count": 1117 }, "SoccerTwos.Step.sum": { "value": 11169974.0, "min": 9570.0, "max": 11169974.0, "count": 1117 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.033499181270599365, "min": -0.11869743466377258, "max": 0.15602651238441467, "count": 1117 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -7.637813568115234, "min": -21.46139907836914, "max": 22.82703399658203, "count": 1117 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.02998179756104946, "min": -0.12342483550310135, "max": 0.14840447902679443, "count": 1117 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -6.835849761962891, "min": -21.431331634521484, "max": 22.890085220336914, "count": 1117 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1117 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1117 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.09124210633729633, "min": -0.4438857152348473, "max": 0.479200002759002, "count": 1117 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -20.803200244903564, "min": -60.52840006351471, "max": 67.16500049829483, "count": 1117 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.09124210633729633, "min": -0.4438857152348473, "max": 0.479200002759002, "count": 1117 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -20.803200244903564, "min": -60.52840006351471, "max": 67.16500049829483, "count": 1117 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1117 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1117 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.020101825617409, "min": 0.011153122591106996, "max": 0.023868167467298917, "count": 539 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.020101825617409, "min": 0.011153122591106996, "max": 0.023868167467298917, "count": 539 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11902831718325615, "min": 2.577112907905151e-06, "max": 0.1321904664238294, "count": 539 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11902831718325615, "min": 2.577112907905151e-06, "max": 0.1321904664238294, "count": 539 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.12089589461684228, "min": 5.975091554925408e-06, "max": 0.13606064369281132, "count": 539 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.12089589461684228, "min": 5.975091554925408e-06, "max": 0.13606064369281132, "count": 539 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 539 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 539 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 539 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 539 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 539 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 539 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1707128678", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/abragin/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1707147791" }, "total": 19113.665000750218, "count": 1, "self": 0.10705320304259658, "children": { "run_training.setup": { "total": 0.00941597018390894, "count": 1, "self": 0.00941597018390894 }, "TrainerController.start_learning": { "total": 19113.54853157699, "count": 1, "self": 12.653861391358078, "children": { "TrainerController._reset_env": { "total": 2.53149905288592, "count": 56, "self": 2.53149905288592 }, "TrainerController.advance": { "total": 19098.252023634966, "count": 768562, "self": 10.504401659127325, "children": { "env_step": { "total": 7862.435224980116, "count": 768562, "self": 6292.333217664156, "children": { "SubprocessEnvManager._take_step": { "total": 1562.6804287093692, "count": 768562, "self": 58.20337650086731, "children": { "TorchPolicy.evaluate": { "total": 1504.4770522085018, "count": 1406722, "self": 1504.4770522085018 } } }, "workers": { "total": 7.421578606590629, "count": 768561, "self": 0.0, "children": { "worker_root": { "total": 19099.829939397983, "count": 768561, "is_parallel": true, "self": 14048.566497283522, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019616824574768543, "count": 2, "is_parallel": true, "self": 0.0005305069498717785, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014311755076050758, "count": 8, "is_parallel": true, "self": 0.0014311755076050758 } } }, "UnityEnvironment.step": { "total": 0.016289445105940104, "count": 1, "is_parallel": true, "self": 0.0003385818563401699, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00034201890230178833, "count": 1, "is_parallel": true, "self": 0.00034201890230178833 }, "communicator.exchange": { "total": 0.014572937972843647, "count": 1, "is_parallel": true, "self": 0.014572937972843647 }, "steps_from_proto": { "total": 0.0010359063744544983, "count": 2, "is_parallel": true, "self": 0.00022473791614174843, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008111684583127499, "count": 8, "is_parallel": true, "self": 0.0008111684583127499 } } } } } } }, "UnityEnvironment.step": { "total": 5051.167801615316, "count": 768560, "is_parallel": true, "self": 308.7718152431771, "children": { "UnityEnvironment._generate_step_input": { "total": 209.96318291453645, "count": 768560, "is_parallel": true, "self": 209.96318291453645 }, "communicator.exchange": { "total": 3635.2505905986764, "count": 768560, "is_parallel": true, "self": 3635.2505905986764 }, "steps_from_proto": { "total": 897.1822128589265, "count": 1537120, "is_parallel": true, "self": 168.52722144313157, "children": { "_process_rank_one_or_two_observation": { "total": 728.6549914157949, "count": 6148480, "is_parallel": true, "self": 728.6549914157949 } } } } }, "steps_from_proto": { "total": 0.09564049914479256, "count": 110, "is_parallel": true, "self": 0.018415361177176237, "children": { "_process_rank_one_or_two_observation": { "total": 0.07722513796761632, "count": 440, "is_parallel": true, "self": 0.07722513796761632 } } } } } } } } }, "trainer_advance": { "total": 11225.312396995723, "count": 768561, "self": 101.76328072044998, "children": { "process_trajectory": { "total": 1761.4239688902162, "count": 768561, "self": 1758.192041605711, "children": { "RLTrainer._checkpoint": { "total": 3.2319272845052183, "count": 22, "self": 3.2319272845052183 } } }, "_update_policy": { "total": 9362.125147385057, "count": 539, "self": 834.941310225986, "children": { "TorchPOCAOptimizer.update": { "total": 8527.183837159071, "count": 16170, "self": 8527.183837159071 } } } } } } }, "trainer_threads": { "total": 6.207264959812164e-07, "count": 1, "self": 6.207264959812164e-07 }, "TrainerController._save_models": { "total": 0.11114687705412507, "count": 1, "self": 0.0008804742246866226, "children": { "RLTrainer._checkpoint": { "total": 0.11026640282943845, "count": 1, "self": 0.11026640282943845 } } } } } } }