{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.9824453592300415, "min": 1.8739594221115112, "max": 1.9862821102142334, "count": 809 }, "SoccerTwos.Policy.Entropy.sum": { "value": 47261.49609375, "min": 28590.546875, "max": 53229.98828125, "count": 809 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 60.3974358974359, "min": 48.78, "max": 91.82142857142857, "count": 809 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 18844.0, "min": 12724.0, "max": 21204.0, "count": 809 }, "SoccerTwos.Self-play.ELO.mean": { "value": 200.69807122695505, "min": 160.45223766886883, "max": 221.11645994002805, "count": 809 }, "SoccerTwos.Self-play.ELO.sum": { "value": 31308.899111404986, "min": 19529.90994427994, "max": 40985.056697454515, "count": 809 }, "SoccerTwos.Step.mean": { "value": 158899961.0, "min": 150819962.0, "max": 158899961.0, "count": 809 }, "SoccerTwos.Step.sum": { "value": 158899961.0, "min": 150819962.0, "max": 158899961.0, "count": 809 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.018284762278199196, "min": -0.21704299747943878, "max": 0.03359431400895119, "count": 809 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -2.8707077503204346, "min": -36.11267852783203, "max": 5.475872993469238, "count": 809 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.03882867470383644, "min": -0.2731809616088867, "max": 0.03336219862103462, "count": 809 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -6.096101760864258, "min": -49.92552947998047, "max": 5.438038349151611, "count": 809 }, "SoccerTwos.Policy.CuriosityBaselineEstimate.mean": { "value": 1.2157836863480043e-05, "min": -0.006319624371826649, "max": 0.028939656913280487, "count": 809 }, "SoccerTwos.Policy.CuriosityBaselineEstimate.sum": { "value": 0.0019087804248556495, "min": -1.1164512634277344, "max": 5.231081008911133, "count": 809 }, "SoccerTwos.Policy.CuriosityValueEstimate.mean": { "value": 5.69396479477291e-06, "min": -0.006349184550344944, "max": 0.02884219028055668, "count": 809 }, "SoccerTwos.Policy.CuriosityValueEstimate.sum": { "value": 0.0008939524996094406, "min": -1.119166374206543, "max": 5.209883689880371, "count": 809 }, "SoccerTwos.Policy.RndBaselineEstimate.mean": { "value": 8.368616363441106e-06, "min": -0.00480329105630517, "max": 0.0183656495064497, "count": 809 }, "SoccerTwos.Policy.RndBaselineEstimate.sum": { "value": 0.0013138727517798543, "min": -0.8429449796676636, "max": 2.9267921447753906, "count": 809 }, "SoccerTwos.Policy.RndValueEstimate.mean": { "value": 1.1133872249047272e-05, "min": -0.004795185290277004, "max": 0.0181350726634264, "count": 809 }, "SoccerTwos.Policy.RndValueEstimate.sum": { "value": 0.001748017966747284, "min": -0.8428221940994263, "max": 2.9356842041015625, "count": 809 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 809 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 809 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.1667643314713885, "min": -0.3838250016172727, "max": 0.2926405072212219, "count": 809 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 26.182000041007996, "min": -57.72960007190704, "max": 46.237200140953064, "count": 809 }, "SoccerTwos.Policy.CuriosityReward.mean": { "value": 2.6344333327928046e-06, "min": 0.0, "max": 7.510302272501776e-06, "count": 809 }, "SoccerTwos.Policy.CuriosityReward.sum": { "value": 0.00041360603324847034, "min": 0.0, "max": 0.001016018376105876, "count": 809 }, "SoccerTwos.Policy.RndReward.mean": { "value": 1.084395531976697e-06, "min": 8.522362944063389e-07, "max": 1.6413188463521214e-06, "count": 809 }, "SoccerTwos.Policy.RndReward.sum": { "value": 0.00017025009852034145, "min": 0.00011363447274703731, "max": 0.00020103728658682485, "count": 809 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.1667643314713885, "min": -0.3838250016172727, "max": 0.2926405072212219, "count": 809 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 26.182000041007996, "min": -57.72960007190704, "max": 46.237200140953064, "count": 809 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 809 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 809 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01488200124974052, "min": 0.004595218287755011, "max": 0.05061443419092231, "count": 49 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01488200124974052, "min": 0.004595218287755011, "max": 0.05061443419092231, "count": 49 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.02260305318567488, "min": 0.022456115318669215, "max": 0.024703273756636515, "count": 49 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.02260305318567488, "min": 0.022456115318669215, "max": 0.024703273756636515, "count": 49 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.023345176751414936, "min": 0.023041918666826353, "max": 0.027839177805516455, "count": 49 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.023345176751414936, "min": 0.023041918666826353, "max": 0.027839177805516455, "count": 49 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 49 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 49 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.3, "min": 0.3, "max": 0.3, "count": 49 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.3, "min": 0.3, "max": 0.3, "count": 49 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.00492078891964, "min": 0.00492078891964, "max": 0.004924663299352, "count": 49 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.00492078891964, "min": 0.00492078891964, "max": 0.004924663299352, "count": 49 }, "SoccerTwos.Losses.CuriosityForwardLoss.mean": { "value": 0.04242806674705611, "min": 0.0423487921555837, "max": 0.12206676105658214, "count": 49 }, "SoccerTwos.Losses.CuriosityForwardLoss.sum": { "value": 0.04242806674705611, "min": 0.0423487921555837, "max": 0.12206676105658214, "count": 49 }, "SoccerTwos.Losses.CuriosityInverseLoss.mean": { "value": 1.361588226424323, "min": 1.3439784447352092, "max": 1.7959681616889105, "count": 49 }, "SoccerTwos.Losses.CuriosityInverseLoss.sum": { "value": 1.361588226424323, "min": 1.3439784447352092, "max": 1.7959681616889105, "count": 49 }, "SoccerTwos.Losses.RNDLoss.mean": { "value": 0.015596083365380764, "min": 0.015499476343393326, "max": 0.017794109880924225, "count": 49 }, "SoccerTwos.Losses.RNDLoss.sum": { "value": 0.015596083365380764, "min": 0.015499476343393326, "max": 0.017794109880924225, "count": 49 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1726918206", "python_version": "3.10.12 (main, Aug 23 2024, 16:29:11) [Clang 15.0.0 (clang-1500.3.9.4)]", "command_line_arguments": "/Users/brettgohre/Desktop/huggingface/ml-agents/games/bin/mlagents-learn ./config/poca/sept/three.yaml --env=./SoccerTwos/SoccerTwos.app --run-id=sept-run-01 --resume --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.0", "numpy_version": "1.23.5", "end_time_seconds": "1726955045" }, "total": 36838.19481516699, "count": 1, "self": 0.011806167894974351, "children": { "run_training.setup": { "total": 0.019822541042231023, "count": 1, "self": 0.019822541042231023 }, "TrainerController.start_learning": { "total": 36838.163186458056, "count": 1, "self": 5.2826125882565975, "children": { "TrainerController._reset_env": { "total": 35.27890009281691, "count": 800, "self": 35.27890009281691 }, "TrainerController.advance": { "total": 36797.39307248499, "count": 598528, "self": 4.700941964518279, "children": { "env_step": { "total": 24404.411351914983, "count": 598528, "self": 23575.48067614867, "children": { "SubprocessEnvManager._take_step": { "total": 825.7377529452788, "count": 598528, "self": 32.30438491667155, "children": { "TorchPolicy.evaluate": { "total": 793.4333680286072, "count": 1099898, "self": 793.4333680286072 } } }, "workers": { "total": 3.1929228210356086, "count": 598528, "self": 0.0, "children": { "worker_root": { "total": 36683.921793210204, "count": 598528, "is_parallel": true, "self": 13739.314992137952, "children": { "steps_from_proto": { "total": 1.0775862756418064, "count": 1600, "is_parallel": true, "self": 0.13856924686115235, "children": { "_process_rank_one_or_two_observation": { "total": 0.9390170287806541, "count": 6400, "is_parallel": true, "self": 0.9390170287806541 } } }, "UnityEnvironment.step": { "total": 22943.52921479661, "count": 598528, "is_parallel": true, "self": 59.51802136620972, "children": { "UnityEnvironment._generate_step_input": { "total": 450.8881625722861, "count": 598528, "is_parallel": true, "self": 450.8881625722861 }, "communicator.exchange": { "total": 21693.82560560596, "count": 598528, "is_parallel": true, "self": 21693.82560560596 }, "steps_from_proto": { "total": 739.2974252521526, "count": 1197056, "is_parallel": true, "self": 88.14237605035305, "children": { "_process_rank_one_or_two_observation": { "total": 651.1550492017996, "count": 4788224, "is_parallel": true, "self": 651.1550492017996 } } } } } } } } } } }, "trainer_advance": { "total": 12388.280778605491, "count": 598528, "self": 48.189471200923435, "children": { "process_trajectory": { "total": 1782.4633543648524, "count": 598528, "self": 1780.4024058259092, "children": { "RLTrainer._checkpoint": { "total": 2.060948538943194, "count": 16, "self": 2.060948538943194 } } }, "_update_policy": { "total": 10557.627953039715, "count": 50, "self": 793.9571674687322, "children": { "TorchPOCAOptimizer.update": { "total": 9763.670785570983, "count": 447, "self": 9763.670785570983 } } } } } } }, "trainer_threads": { "total": 1.00000761449337e-06, "count": 1, "self": 1.00000761449337e-06 }, "TrainerController._save_models": { "total": 0.20860029198229313, "count": 1, "self": 0.0029710419476032257, "children": { "RLTrainer._checkpoint": { "total": 0.2056292500346899, "count": 1, "self": 0.2056292500346899 } } } } } } }