{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.8133866786956787, "min": 1.8133866786956787, "max": 3.2957496643066406, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 37022.1015625, "min": 21899.626953125, "max": 129072.6796875, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 51.677083333333336, "min": 43.49557522123894, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19844.0, "min": 14856.0, "max": 26616.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1583.2591328881092, "min": 1186.902705196918, "max": 1593.3667897650848, "count": 493 }, "SoccerTwos.Self-play.ELO.sum": { "value": 303985.753514517, "min": 2373.805410393836, "max": 339933.3672600968, "count": 493 }, "SoccerTwos.Step.mean": { "value": 4999982.0, "min": 9330.0, "max": 4999982.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999982.0, "min": 9330.0, "max": 4999982.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.03343738615512848, "min": -0.09077697992324829, "max": 0.1848892867565155, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 6.386540412902832, "min": -16.06752586364746, "max": 41.56588363647461, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.035941898822784424, "min": -0.08798559755086899, "max": 0.19318944215774536, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 6.864902973175049, "min": -15.80552864074707, "max": 43.66081237792969, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.017285863142363064, "min": -0.5991578949125189, "max": 0.5558163963380407, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -3.301599860191345, "min": -47.43159997463226, "max": 77.27679944038391, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.017285863142363064, "min": -0.5991578949125189, "max": 0.5558163963380407, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -3.301599860191345, "min": -47.43159997463226, "max": 77.27679944038391, "count": 500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017720330889278556, "min": 0.011217654222855344, "max": 0.02328540737895916, "count": 240 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017720330889278556, "min": 0.011217654222855344, "max": 0.02328540737895916, "count": 240 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09902165581782658, "min": 0.0005704073182035547, "max": 0.11834300259749095, "count": 240 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09902165581782658, "min": 0.0005704073182035547, "max": 0.11834300259749095, "count": 240 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10045446703831355, "min": 0.0005726657070529958, "max": 0.12040329898397127, "count": 240 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10045446703831355, "min": 0.0005726657070529958, "max": 0.12040329898397127, "count": 240 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 240 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 240 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 240 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 240 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 240 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 240 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1711274750", "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\Hosein\\anaconda3\\envs\\ml_agents_env\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1711284757" }, "total": 10006.498496100001, "count": 1, "self": 0.3042918999999529, "children": { "run_training.setup": { "total": 0.12596920000214595, "count": 1, "self": 0.12596920000214595 }, "TrainerController.start_learning": { "total": 10006.068234999999, "count": 1, "self": 6.93693239942877, "children": { "TrainerController._reset_env": { "total": 6.484243800005061, "count": 25, "self": 6.484243800005061 }, "TrainerController.advance": { "total": 9992.459395300571, "count": 341422, "self": 6.797262996493373, "children": { "env_step": { "total": 7431.051334502161, "count": 341422, "self": 4362.111070500487, "children": { "SubprocessEnvManager._take_step": { "total": 3064.452701001166, "count": 341422, "self": 40.4734161001179, "children": { "TorchPolicy.evaluate": { "total": 3023.9792849010482, "count": 631128, "self": 3023.9792849010482 } } }, "workers": { "total": 4.487563000508089, "count": 341422, "self": 0.0, "children": { "worker_root": { "total": 9992.240323700255, "count": 341422, "is_parallel": true, "self": 6485.705728001758, "children": { "steps_from_proto": { "total": 0.04412820001016371, "count": 50, "is_parallel": true, "self": 0.008624300033261534, "children": { "_process_rank_one_or_two_observation": { "total": 0.035503899976902176, "count": 200, "is_parallel": true, "self": 0.035503899976902176 } } }, "UnityEnvironment.step": { "total": 3506.4904674984864, "count": 341422, "is_parallel": true, "self": 167.9950418963017, "children": { "UnityEnvironment._generate_step_input": { "total": 141.58313099854786, "count": 341422, "is_parallel": true, "self": 141.58313099854786 }, "communicator.exchange": { "total": 2655.4528280009727, "count": 341422, "is_parallel": true, "self": 2655.4528280009727 }, "steps_from_proto": { "total": 541.4594666026642, "count": 682844, "is_parallel": true, "self": 110.00853120071042, "children": { "_process_rank_one_or_two_observation": { "total": 431.45093540195376, "count": 2731376, "is_parallel": true, "self": 431.45093540195376 } } } } } } } } } } }, "trainer_advance": { "total": 2554.610797801917, "count": 341422, "self": 49.9237516022331, "children": { "process_trajectory": { "total": 1329.3054332996908, "count": 341422, "self": 1327.3149899997043, "children": { "RLTrainer._checkpoint": { "total": 1.9904432999865094, "count": 10, "self": 1.9904432999865094 } } }, "_update_policy": { "total": 1175.3816128999933, "count": 240, "self": 624.3163912998789, "children": { "TorchPOCAOptimizer.update": { "total": 551.0652216001145, "count": 7200, "self": 551.0652216001145 } } } } } } }, "trainer_threads": { "total": 1.0000003385357559e-06, "count": 1, "self": 1.0000003385357559e-06 }, "TrainerController._save_models": { "total": 0.18766249999316642, "count": 1, "self": 0.006767299993953202, "children": { "RLTrainer._checkpoint": { "total": 0.18089519999921322, "count": 1, "self": 0.18089519999921322 } } } } } } }