{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.9022620916366577, "min": 1.8399730920791626, "max": 3.295743703842163, "count": 2000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 42123.69140625, "min": 13083.54296875, "max": 155907.515625, "count": 2000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 60.1625, "min": 42.06896551724138, "max": 999.0, "count": 2000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19252.0, "min": 16328.0, "max": 23748.0, "count": 2000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1704.7144194361822, "min": 1165.8354146542647, "max": 1740.558961926563, "count": 1436 }, "SoccerTwos.Self-play.ELO.sum": { "value": 272754.30710978917, "min": 2331.6708293085294, "max": 388919.1576619488, "count": 1436 }, "SoccerTwos.Step.mean": { "value": 19999973.0, "min": 9078.0, "max": 19999973.0, "count": 2000 }, "SoccerTwos.Step.sum": { "value": 19999973.0, "min": 9078.0, "max": 19999973.0, "count": 2000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.06095085293054581, "min": -0.11376042664051056, "max": 0.48827940225601196, "count": 2000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -9.75213623046875, "min": -17.645727157592773, "max": 94.94754028320312, "count": 2000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0613497719168663, "min": -0.11459508538246155, "max": 0.4999018907546997, "count": 2000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -9.815963745117188, "min": -17.122785568237305, "max": 96.8167724609375, "count": 2000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.08458999991416931, "min": -0.85, "max": 0.9498212129780741, "count": 2000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -13.53439998626709, "min": -49.7888001203537, "max": 201.04660022258759, "count": 2000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.08458999991416931, "min": -0.85, "max": 0.9498212129780741, "count": 2000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -13.53439998626709, "min": -49.7888001203537, "max": 201.04660022258759, "count": 2000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.02249792498187162, "min": 0.010341560510278213, "max": 0.02375247816865643, "count": 941 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.02249792498187162, "min": 0.010341560510278213, "max": 0.02375247816865643, "count": 941 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08072768151760101, "min": 6.8399004978421845e-09, "max": 0.10939825077851613, "count": 941 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.08072768151760101, "min": 6.8399004978421845e-09, "max": 0.10939825077851613, "count": 941 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.08232991024851799, "min": 2.002118068370843e-08, "max": 0.11166551013787587, "count": 941 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.08232991024851799, "min": 2.002118068370843e-08, "max": 0.11166551013787587, "count": 941 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 941 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 941 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 941 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 941 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 941 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 941 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675714946", "python_version": "3.9.13 (tags/v3.9.13:6de2ca5, May 17 2022, 16:36:42) [MSC v.1929 64 bit (AMD64)]", "command_line_arguments": "D:\\python\\mlagents\\scripts\\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": "1.13.1+cu117", "numpy_version": "1.21.2", "end_time_seconds": "1675775331" }, "total": 60384.9729408, "count": 1, "self": 1.5158330999911414, "children": { "run_training.setup": { "total": 0.21047610000000017, "count": 1, "self": 0.21047610000000017 }, "TrainerController.start_learning": { "total": 60383.24663160001, "count": 1, "self": 41.31832599914924, "children": { "TrainerController._reset_env": { "total": 11.089936600013925, "count": 58, "self": 11.089936600013925 }, "TrainerController.advance": { "total": 60330.46756850084, "count": 1317751, "self": 41.99330479697528, "children": { "env_step": { "total": 43529.7071154034, "count": 1317751, "self": 24153.399586606967, "children": { "SubprocessEnvManager._take_step": { "total": 19350.326268597233, "count": 1317751, "self": 296.64081670070664, "children": { "TorchPolicy.evaluate": { "total": 19053.685451896527, "count": 2534374, "self": 19053.685451896527 } } }, "workers": { "total": 25.98126019919969, "count": 1317751, "self": 0.0, "children": { "worker_root": { "total": 60317.74843109811, "count": 1317751, "is_parallel": true, "self": 41465.77858609866, "children": { "steps_from_proto": { "total": 0.14078900002736994, "count": 116, "is_parallel": true, "self": 0.03195079996222816, "children": { "_process_rank_one_or_two_observation": { "total": 0.10883820006514178, "count": 464, "is_parallel": true, "self": 0.10883820006514178 } } }, "UnityEnvironment.step": { "total": 18851.82905599942, "count": 1317751, "is_parallel": true, "self": 951.2304792046234, "children": { "UnityEnvironment._generate_step_input": { "total": 919.3281762954023, "count": 1317751, "is_parallel": true, "self": 919.3281762954023 }, "communicator.exchange": { "total": 13876.2674867984, "count": 1317751, "is_parallel": true, "self": 13876.2674867984 }, "steps_from_proto": { "total": 3105.002913700994, "count": 2635502, "is_parallel": true, "self": 702.2630704055841, "children": { "_process_rank_one_or_two_observation": { "total": 2402.73984329541, "count": 10542008, "is_parallel": true, "self": 2402.73984329541 } } } } } } } } } } }, "trainer_advance": { "total": 16758.767148300467, "count": 1317751, "self": 302.4858820012996, "children": { "process_trajectory": { "total": 5913.176311299255, "count": 1317751, "self": 5898.438493199246, "children": { "RLTrainer._checkpoint": { "total": 14.73781810000878, "count": 40, "self": 14.73781810000878 } } }, "_update_policy": { "total": 10543.104954999913, "count": 941, "self": 5346.729310200355, "children": { "TorchPOCAOptimizer.update": { "total": 5196.375644799558, "count": 28233, "self": 5196.375644799558 } } } } } } }, "trainer_threads": { "total": 2.5000044843181968e-06, "count": 1, "self": 2.5000044843181968e-06 }, "TrainerController._save_models": { "total": 0.3707979999962845, "count": 1, "self": 0.012650599994231015, "children": { "RLTrainer._checkpoint": { "total": 0.3581474000020535, "count": 1, "self": 0.3581474000020535 } } } } } } }