{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.7357258796691895, "min": 1.7357258796691895, "max": 3.2957262992858887, "count": 499 }, "SoccerTwos.Policy.Entropy.sum": { "value": 36047.5546875, "min": 32399.783203125, "max": 109138.140625, "count": 499 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 58.55294117647059, "min": 40.17213114754098, "max": 999.0, "count": 499 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19908.0, "min": 11988.0, "max": 30524.0, "count": 499 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1535.2464879623687, "min": 1185.846390589392, "max": 1535.2464879623687, "count": 496 }, "SoccerTwos.Self-play.ELO.sum": { "value": 260991.9029536027, "min": 2373.534359086861, "max": 369363.51837170986, "count": 496 }, "SoccerTwos.Step.mean": { "value": 4999972.0, "min": 9776.0, "max": 4999972.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999972.0, "min": 9776.0, "max": 4999972.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0489937886595726, "min": -0.11460649222135544, "max": 0.22853006422519684, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -8.426931381225586, "min": -24.755002975463867, "max": 29.675430297851562, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.05757222697138786, "min": -0.11096495389938354, "max": 0.237616628408432, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -9.902422904968262, "min": -23.968429565429688, "max": 28.671131134033203, "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": -0.028499998325525328, "min": -0.6227789474161047, "max": 0.5738772722807798, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -4.9019997119903564, "min": -64.19199997186661, "max": 66.64039999246597, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.028499998325525328, "min": -0.6227789474161047, "max": 0.5738772722807798, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -4.9019997119903564, "min": -64.19199997186661, "max": 66.64039999246597, "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": 0.013779122809273759, "min": 0.012906821083743126, "max": 0.02480651108926395, "count": 240 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.013779122809273759, "min": 0.012906821083743126, "max": 0.02480651108926395, "count": 240 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10436656214296818, "min": 0.001162040299095679, "max": 0.12384975887835026, "count": 240 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10436656214296818, "min": 0.001162040299095679, "max": 0.12384975887835026, "count": 240 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10845585595816373, "min": 0.001197706248058239, "max": 0.12881805654615164, "count": 240 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10845585595816373, "min": 0.001197706248058239, "max": 0.12881805654615164, "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": 0.2, "min": 0.19999999999999993, "max": 0.2, "count": 240 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.2, "min": 0.19999999999999993, "max": 0.2, "count": 240 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005, "min": 0.005, "max": 0.005000000000000001, "count": 240 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005, "min": 0.005, "max": 0.005000000000000001, "count": 240 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1682328633", "python_version": "3.9.16 (main, Mar 8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\butterp\\Miniconda3\\envs\\hf-rl-unit7\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos_2 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.0+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1682341616" }, "total": 12983.7611971, "count": 1, "self": 0.30598400000053516, "children": { "run_training.setup": { "total": 0.13067969999999995, "count": 1, "self": 0.13067969999999995 }, "TrainerController.start_learning": { "total": 12983.3245334, "count": 1, "self": 6.490294800551055, "children": { "TrainerController._reset_env": { "total": 4.313939400003633, "count": 25, "self": 4.313939400003633 }, "TrainerController.advance": { "total": 12972.358244399444, "count": 343450, "self": 6.097982998544467, "children": { "env_step": { "total": 4186.941732400504, "count": 343450, "self": 3280.0181609008637, "children": { "SubprocessEnvManager._take_step": { "total": 903.2840843999162, "count": 343450, "self": 36.54602539923428, "children": { "TorchPolicy.evaluate": { "total": 866.7380590006819, "count": 630330, "self": 866.7380590006819 } } }, "workers": { "total": 3.6394870997246462, "count": 343450, "self": 0.0, "children": { "worker_root": { "total": 12970.962692999854, "count": 343450, "is_parallel": true, "self": 10374.93742119908, "children": { "steps_from_proto": { "total": 0.03437790000052132, "count": 50, "is_parallel": true, "self": 0.007046699999041284, "children": { "_process_rank_one_or_two_observation": { "total": 0.027331200001480038, "count": 200, "is_parallel": true, "self": 0.027331200001480038 } } }, "UnityEnvironment.step": { "total": 2595.990893900773, "count": 343450, "is_parallel": true, "self": 130.74976610110843, "children": { "UnityEnvironment._generate_step_input": { "total": 110.95740499983543, "count": 343450, "is_parallel": true, "self": 110.95740499983543 }, "communicator.exchange": { "total": 1950.9172994999685, "count": 343450, "is_parallel": true, "self": 1950.9172994999685 }, "steps_from_proto": { "total": 403.36642329986034, "count": 686900, "is_parallel": true, "self": 81.72282649826872, "children": { "_process_rank_one_or_two_observation": { "total": 321.6435968015916, "count": 2747600, "is_parallel": true, "self": 321.6435968015916 } } } } } } } } } } }, "trainer_advance": { "total": 8779.318529000395, "count": 343450, "self": 51.85962010053299, "children": { "process_trajectory": { "total": 1077.5200250998605, "count": 343450, "self": 1075.86798259986, "children": { "RLTrainer._checkpoint": { "total": 1.6520425000005616, "count": 10, "self": 1.6520425000005616 } } }, "_update_policy": { "total": 7649.938883800001, "count": 240, "self": 828.8249477000672, "children": { "TorchPOCAOptimizer.update": { "total": 6821.113936099934, "count": 9620, "self": 6821.113936099934 } } } } } } }, "trainer_threads": { "total": 8.000006346264854e-07, "count": 1, "self": 8.000006346264854e-07 }, "TrainerController._save_models": { "total": 0.16205400000035297, "count": 1, "self": 0.01783660000000964, "children": { "RLTrainer._checkpoint": { "total": 0.14421740000034333, "count": 1, "self": 0.14421740000034333 } } } } } } }