{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.601577877998352, "min": 1.5636346340179443, "max": 3.295750856399536, "count": 1003 }, "SoccerTwos.Policy.Entropy.sum": { "value": 32339.060546875, "min": 15664.6953125, "max": 112831.828125, "count": 1003 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 58.627906976744185, "min": 36.02962962962963, "max": 999.0, "count": 1003 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20168.0, "min": 14004.0, "max": 26060.0, "count": 1003 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1623.1869950634712, "min": 1195.8593302065567, "max": 1671.6834722475915, "count": 983 }, "SoccerTwos.Self-play.ELO.sum": { "value": 279188.16315091704, "min": 2392.3790637106417, "max": 423211.87002880627, "count": 983 }, "SoccerTwos.Step.mean": { "value": 10029706.0, "min": 9048.0, "max": 10029706.0, "count": 1003 }, "SoccerTwos.Step.sum": { "value": 10029706.0, "min": 9048.0, "max": 10029706.0, "count": 1003 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.016616741195321083, "min": -0.11547587066888809, "max": 0.19086655974388123, "count": 1003 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -2.858079433441162, "min": -23.788028717041016, "max": 29.637088775634766, "count": 1003 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.013339678756892681, "min": -0.11674820631742477, "max": 0.19290082156658173, "count": 1003 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -2.2944247722625732, "min": -24.05013084411621, "max": 29.790895462036133, "count": 1003 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1003 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1003 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.01914418436760126, "min": -0.5213866670926411, "max": 0.6197111085057259, "count": 1003 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 3.292799711227417, "min": -54.46280014514923, "max": 54.36500072479248, "count": 1003 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.01914418436760126, "min": -0.5213866670926411, "max": 0.6197111085057259, "count": 1003 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 3.292799711227417, "min": -54.46280014514923, "max": 54.36500072479248, "count": 1003 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1003 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1003 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015971961586425703, "min": 0.011165675827457259, "max": 0.023715842918803295, "count": 483 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015971961586425703, "min": 0.011165675827457259, "max": 0.023715842918803295, "count": 483 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.1058881791929404, "min": 9.719703848531936e-06, "max": 0.12382420475284259, "count": 483 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.1058881791929404, "min": 9.719703848531936e-06, "max": 0.12382420475284259, "count": 483 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10714588115612665, "min": 1.0255586797332702e-05, "max": 0.12667151143153507, "count": 483 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10714588115612665, "min": 1.0255586797332702e-05, "max": 0.12667151143153507, "count": 483 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 483 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 483 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 483 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 483 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 483 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 483 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1693248900", "python_version": "3.9.17 | packaged by conda-forge | (main, Aug 10 2023, 07:02:31) \n[GCC 12.3.0]", "command_line_arguments": "/home/webdev/mambaforge/envs/HFU7/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/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": "1693277931" }, "total": 29031.620333282, "count": 1, "self": 0.05287812399910763, "children": { "run_training.setup": { "total": 0.009515609999652952, "count": 1, "self": 0.009515609999652952 }, "TrainerController.start_learning": { "total": 29031.557939548, "count": 1, "self": 18.175838661936723, "children": { "TrainerController._reset_env": { "total": 2.156283196993172, "count": 51, "self": 2.156283196993172 }, "TrainerController.advance": { "total": 29011.01186484007, "count": 688680, "self": 18.19091983104954, "children": { "env_step": { "total": 10782.167248136095, "count": 688680, "self": 8597.337880749792, "children": { "SubprocessEnvManager._take_step": { "total": 2174.479044507286, "count": 688680, "self": 85.00831666234353, "children": { "TorchPolicy.evaluate": { "total": 2089.4707278449423, "count": 1264134, "self": 2089.4707278449423 } } }, "workers": { "total": 10.350322879016858, "count": 688680, "self": 0.0, "children": { "worker_root": { "total": 28990.45162019948, "count": 688680, "is_parallel": true, "self": 22156.694621427374, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0023145959994508303, "count": 2, "is_parallel": true, "self": 0.0005671239996445365, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017474719998062938, "count": 8, "is_parallel": true, "self": 0.0017474719998062938 } } }, "UnityEnvironment.step": { "total": 0.025921381000443944, "count": 1, "is_parallel": true, "self": 0.0005362040001273272, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045210500047687674, "count": 1, "is_parallel": true, "self": 0.00045210500047687674 }, "communicator.exchange": { "total": 0.02323471999989124, "count": 1, "is_parallel": true, "self": 0.02323471999989124 }, "steps_from_proto": { "total": 0.0016983519999484997, "count": 2, "is_parallel": true, "self": 0.00039471499894716544, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013036370010013343, "count": 8, "is_parallel": true, "self": 0.0013036370010013343 } } } } } } }, "UnityEnvironment.step": { "total": 6833.672253721114, "count": 688679, "is_parallel": true, "self": 364.2248479545833, "children": { "UnityEnvironment._generate_step_input": { "total": 255.25064751194077, "count": 688679, "is_parallel": true, "self": 255.25064751194077 }, "communicator.exchange": { "total": 5147.227819189504, "count": 688679, "is_parallel": true, "self": 5147.227819189504 }, "steps_from_proto": { "total": 1066.9689390650865, "count": 1377358, "is_parallel": true, "self": 238.2093864804374, "children": { "_process_rank_one_or_two_observation": { "total": 828.7595525846491, "count": 5509432, "is_parallel": true, "self": 828.7595525846491 } } } } }, "steps_from_proto": { "total": 0.0847450509927512, "count": 100, "is_parallel": true, "self": 0.018489625949769106, "children": { "_process_rank_one_or_two_observation": { "total": 0.0662554250429821, "count": 400, "is_parallel": true, "self": 0.0662554250429821 } } } } } } } } }, "trainer_advance": { "total": 18210.653696872927, "count": 688680, "self": 131.16370465547516, "children": { "process_trajectory": { "total": 2630.6715978244383, "count": 688680, "self": 2626.737615402437, "children": { "RLTrainer._checkpoint": { "total": 3.9339824220014634, "count": 20, "self": 3.9339824220014634 } } }, "_update_policy": { "total": 15448.818394393013, "count": 484, "self": 1496.9449924147339, "children": { "TorchPOCAOptimizer.update": { "total": 13951.873401978279, "count": 14503, "self": 13951.873401978279 } } } } } } }, "trainer_threads": { "total": 1.1840020306408405e-06, "count": 1, "self": 1.1840020306408405e-06 }, "TrainerController._save_models": { "total": 0.21395166499860352, "count": 1, "self": 0.0018202789942733943, "children": { "RLTrainer._checkpoint": { "total": 0.21213138600433012, "count": 1, "self": 0.21213138600433012 } } } } } } }