{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.6256786584854126, "min": 1.5642390251159668, "max": 3.2957377433776855, "count": 800 }, "SoccerTwos.Policy.Entropy.sum": { "value": 32617.6171875, "min": 17252.240234375, "max": 114944.359375, "count": 800 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 51.473118279569896, "min": 43.14912280701754, "max": 999.0, "count": 800 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19148.0, "min": 16304.0, "max": 23816.0, "count": 800 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1731.875841191476, "min": 1200.0537661875258, "max": 1762.8800600820869, "count": 798 }, "SoccerTwos.Self-play.ELO.sum": { "value": 322128.90646161453, "min": 2401.0604110829995, "max": 393737.32707262714, "count": 798 }, "SoccerTwos.Step.mean": { "value": 7999986.0, "min": 9776.0, "max": 7999986.0, "count": 800 }, "SoccerTwos.Step.sum": { "value": 7999986.0, "min": 9776.0, "max": 7999986.0, "count": 800 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.05115625634789467, "min": -0.11069655418395996, "max": 0.5553528070449829, "count": 800 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -9.463907241821289, "min": -21.807220458984375, "max": 102.74026489257812, "count": 800 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.05258863419294357, "min": -0.10635542869567871, "max": 0.5559619069099426, "count": 800 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -9.728897094726562, "min": -20.95201873779297, "max": 102.85295104980469, "count": 800 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 800 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 800 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.06546378586743329, "min": -0.5290315778631913, "max": 0.9053156788284714, "count": 800 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -12.110800385475159, "min": -66.04340010881424, "max": 190.0378002524376, "count": 800 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.06546378586743329, "min": -0.5290315778631913, "max": 0.9053156788284714, "count": 800 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -12.110800385475159, "min": -66.04340010881424, "max": 190.0378002524376, "count": 800 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 800 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 800 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.021149129086794952, "min": 0.010297381315225115, "max": 0.024658651063024686, "count": 387 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.021149129086794952, "min": 0.010297381315225115, "max": 0.024658651063024686, "count": 387 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10122881134351094, "min": 0.0008497119197272696, "max": 0.1258475050330162, "count": 387 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10122881134351094, "min": 0.0008497119197272696, "max": 0.1258475050330162, "count": 387 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10289162620902062, "min": 0.0008523181852069684, "max": 0.12865025500456492, "count": 387 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10289162620902062, "min": 0.0008523181852069684, "max": 0.12865025500456492, "count": 387 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 387 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 387 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 387 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 387 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 387 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 387 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1690867516", "python_version": "3.9.17 (main, Jul 5 2023, 15:35:09) \n[Clang 14.0.6 ]", "command_line_arguments": "/Users/benjaminchew/miniconda/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/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": "1690890993" }, "total": 23476.685105792, "count": 1, "self": 0.23365299999568379, "children": { "run_training.setup": { "total": 0.013957292000000066, "count": 1, "self": 0.013957292000000066 }, "TrainerController.start_learning": { "total": 23476.437495500002, "count": 1, "self": 5.129147054198256, "children": { "TrainerController._reset_env": { "total": 2.2136632500017663, "count": 15, "self": 2.2136632500017663 }, "TrainerController.advance": { "total": 23469.026639778804, "count": 547763, "self": 4.372223203903559, "children": { "env_step": { "total": 18306.473024395113, "count": 547763, "self": 17572.661596882506, "children": { "SubprocessEnvManager._take_step": { "total": 730.3590117191775, "count": 547763, "self": 20.150978073605074, "children": { "TorchPolicy.evaluate": { "total": 710.2080336455724, "count": 1002370, "self": 710.2080336455724 } } }, "workers": { "total": 3.4524157934291293, "count": 547763, "self": 0.0, "children": { "worker_root": { "total": 23466.77652979186, "count": 547763, "is_parallel": true, "self": 6571.371401407967, "children": { "steps_from_proto": { "total": 0.015487124008218167, "count": 30, "is_parallel": true, "self": 0.002242330007306448, "children": { "_process_rank_one_or_two_observation": { "total": 0.01324479400091172, "count": 120, "is_parallel": true, "self": 0.01324479400091172 } } }, "UnityEnvironment.step": { "total": 16895.389641259884, "count": 547763, "is_parallel": true, "self": 47.19376649975675, "children": { "UnityEnvironment._generate_step_input": { "total": 259.8079845966432, "count": 547763, "is_parallel": true, "self": 259.8079845966432 }, "communicator.exchange": { "total": 16069.486681806688, "count": 547763, "is_parallel": true, "self": 16069.486681806688 }, "steps_from_proto": { "total": 518.9012083567959, "count": 1095526, "is_parallel": true, "self": 70.49038638683822, "children": { "_process_rank_one_or_two_observation": { "total": 448.4108219699577, "count": 4382104, "is_parallel": true, "self": 448.4108219699577 } } } } } } } } } } }, "trainer_advance": { "total": 5158.181392179786, "count": 547763, "self": 40.92365785165748, "children": { "process_trajectory": { "total": 1235.1088307051277, "count": 547763, "self": 1233.8477631201224, "children": { "RLTrainer._checkpoint": { "total": 1.2610675850053212, "count": 16, "self": 1.2610675850053212 } } }, "_update_policy": { "total": 3882.148903623001, "count": 387, "self": 509.5923697880994, "children": { "TorchPOCAOptimizer.update": { "total": 3372.5565338349015, "count": 11610, "self": 3372.5565338349015 } } } } } } }, "trainer_threads": { "total": 3.749992174562067e-07, "count": 1, "self": 3.749992174562067e-07 }, "TrainerController._save_models": { "total": 0.06804504200044903, "count": 1, "self": 0.0007374999986495823, "children": { "RLTrainer._checkpoint": { "total": 0.06730754200179945, "count": 1, "self": 0.06730754200179945 } } } } } } }