{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.5550494194030762, "min": 1.5097248554229736, "max": 3.295724630355835, "count": 1043 }, "SoccerTwos.Policy.Entropy.sum": { "value": 33688.58984375, "min": 9973.49609375, "max": 119995.53125, "count": 1043 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 47.722772277227726, "min": 43.589285714285715, "max": 999.0, "count": 1043 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19280.0, "min": 16280.0, "max": 23724.0, "count": 1043 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1582.8134817847795, "min": 1188.2046971616523, "max": 1619.6439292510802, "count": 890 }, "SoccerTwos.Self-play.ELO.sum": { "value": 319728.32332052547, "min": 2376.4093943233047, "max": 344865.4353870868, "count": 890 }, "SoccerTwos.Step.mean": { "value": 10429966.0, "min": 9854.0, "max": 10429966.0, "count": 1043 }, "SoccerTwos.Step.sum": { "value": 10429966.0, "min": 9854.0, "max": 10429966.0, "count": 1043 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0497281588613987, "min": -0.10054294019937515, "max": 0.1932934820652008, "count": 1043 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -10.094816207885742, "min": -20.209131240844727, "max": 25.514739990234375, "count": 1043 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0484129823744297, "min": -0.10321034491062164, "max": 0.19185669720172882, "count": 1043 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -9.827835083007812, "min": -20.14185905456543, "max": 25.66329574584961, "count": 1043 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1043 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1043 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.04246896534717729, "min": -0.5714285714285714, "max": 0.5170318163705595, "count": 1043 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -8.62119996547699, "min": -62.981199622154236, "max": 76.35160064697266, "count": 1043 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.04246896534717729, "min": -0.5714285714285714, "max": 0.5170318163705595, "count": 1043 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -8.62119996547699, "min": -62.981199622154236, "max": 76.35160064697266, "count": 1043 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1043 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1043 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.013661198940341516, "min": 0.010374464127623165, "max": 0.0227695661461136, "count": 496 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.013661198940341516, "min": 0.010374464127623165, "max": 0.0227695661461136, "count": 496 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.1031475767493248, "min": 5.4046286024345135e-08, "max": 0.11875724320610365, "count": 496 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.1031475767493248, "min": 5.4046286024345135e-08, "max": 0.11875724320610365, "count": 496 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10476672848065695, "min": 6.476436098523664e-08, "max": 0.12022194465001425, "count": 496 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10476672848065695, "min": 6.476436098523664e-08, "max": 0.12022194465001425, "count": 496 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 496 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 496 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 496 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 496 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 496 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 496 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675997137", "python_version": "3.9.16 (main, Jan 11 2023, 10:02:19) \n[Clang 14.0.6 ]", "command_line_arguments": "/Users/viewitpro/projetos/anaconda3/envs/aivai/bin/mlagents-learn ./ml-agents/config/poca/SoccerTwos.yaml --env=./SoccerTwos.app --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": "1676044327" }, "total": 47192.109826961, "count": 1, "self": 0.006378017998940777, "children": { "run_training.setup": { "total": 0.025793116000000005, "count": 1, "self": 0.025793116000000005 }, "TrainerController.start_learning": { "total": 47192.077655827, "count": 1, "self": 18.51457345817471, "children": { "TrainerController._reset_env": { "total": 5.344833142002228, "count": 53, "self": 5.344833142002228 }, "TrainerController.advance": { "total": 47168.02123901282, "count": 702720, "self": 18.98350650608336, "children": { "env_step": { "total": 13055.130606748662, "count": 702720, "self": 10538.316574493947, "children": { "SubprocessEnvManager._take_step": { "total": 2504.853882806192, "count": 702720, "self": 100.46386642695825, "children": { "TorchPolicy.evaluate": { "total": 2404.3900163792337, "count": 1327628, "self": 2404.3900163792337 } } }, "workers": { "total": 11.96014944852324, "count": 702720, "self": 0.0, "children": { "worker_root": { "total": 47114.35815290187, "count": 702720, "is_parallel": true, "self": 38587.86333400732, "children": { "steps_from_proto": { "total": 0.114596869966757, "count": 106, "is_parallel": true, "self": 0.025028603042876352, "children": { "_process_rank_one_or_two_observation": { "total": 0.08956826692388065, "count": 424, "is_parallel": true, "self": 0.08956826692388065 } } }, "UnityEnvironment.step": { "total": 8526.380222024582, "count": 702720, "is_parallel": true, "self": 528.7491229587122, "children": { "UnityEnvironment._generate_step_input": { "total": 368.2595468797558, "count": 702720, "is_parallel": true, "self": 368.2595468797558 }, "communicator.exchange": { "total": 6186.115235615693, "count": 702720, "is_parallel": true, "self": 6186.115235615693 }, "steps_from_proto": { "total": 1443.2563165704216, "count": 1405440, "is_parallel": true, "self": 312.4907815692145, "children": { "_process_rank_one_or_two_observation": { "total": 1130.7655350012071, "count": 5621760, "is_parallel": true, "self": 1130.7655350012071 } } } } } } } } } } }, "trainer_advance": { "total": 34093.90712575808, "count": 702720, "self": 150.98116684947308, "children": { "process_trajectory": { "total": 3677.4997150225577, "count": 702720, "self": 3673.655044992556, "children": { "RLTrainer._checkpoint": { "total": 3.8446700300014527, "count": 20, "self": 3.8446700300014527 } } }, "_update_policy": { "total": 30265.42624388605, "count": 497, "self": 1920.0372157010643, "children": { "TorchPOCAOptimizer.update": { "total": 28345.389028184985, "count": 14901, "self": 28345.389028184985 } } } } } } }, "trainer_threads": { "total": 1.1849988368339837e-06, "count": 1, "self": 1.1849988368339837e-06 }, "TrainerController._save_models": { "total": 0.1970090290051303, "count": 1, "self": 0.0018637570101418532, "children": { "RLTrainer._checkpoint": { "total": 0.19514527199498843, "count": 1, "self": 0.19514527199498843 } } } } } } }