{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": -3.576278402306343e-07, "min": -728.456787109375, "max": 2.3041441440582275, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": -0.00955581571906805, "min": -21189466.0, "max": 59079.8359375, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 999.0, "min": 384.9230769230769, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19980.0, "min": 13884.0, "max": 26392.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1190.8192272646215, "min": 1190.714839363835, "max": 1200.184499346346, "count": 43 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2381.638454529243, "min": 2381.42967872767, "max": 19161.253724858343, "count": 43 }, "SoccerTwos.Step.mean": { "value": 4999762.0, "min": 9532.0, "max": 4999762.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999762.0, "min": 9532.0, "max": 4999762.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -4.271811485290527, "min": -15.753771781921387, "max": 407.4938049316406, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -42.718116760253906, "min": -157.5377197265625, "max": 6398.5126953125, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -4.23355770111084, "min": -15.418455123901367, "max": 437.1966247558594, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -42.33557891845703, "min": -154.18455505371094, "max": 7432.3427734375, "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": 0.0, "min": -0.5833333333333334, "max": 0.15213333566983542, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.0, "min": -7.0, "max": 1.825600028038025, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0, "min": -0.5833333333333334, "max": 0.15213333566983542, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.0, "min": -7.0, "max": 1.825600028038025, "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": 0.016559578662660595, "min": 0.010300619858511103, "max": 1.1859734574953715, "count": 229 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016559578662660595, "min": 0.010300619858511103, "max": 1.1859734574953715, "count": 229 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 5.553191367785136, "min": 0.022181349620223046, "max": 246288.99308217366, "count": 229 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 5.553191367785136, "min": 0.022181349620223046, "max": 246288.99308217366, "count": 229 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 6.254869310061137, "min": 0.022251963118712106, "max": 280135.72156295774, "count": 229 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 6.254869310061137, "min": 0.022251963118712106, "max": 280135.72156295774, "count": 229 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 229 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 229 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 229 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 229 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 229 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 229 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1723835491", "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\\Juan\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos-3 --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+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1723874173" }, "total": 38682.40613440001, "count": 1, "self": 0.40131150001252536, "children": { "run_training.setup": { "total": 0.1988377000016044, "count": 1, "self": 0.1988377000016044 }, "TrainerController.start_learning": { "total": 38681.80598519999, "count": 1, "self": 12.317793899557728, "children": { "TrainerController._reset_env": { "total": 9.187699399990379, "count": 25, "self": 9.187699399990379 }, "TrainerController.advance": { "total": 38660.11652010045, "count": 326114, "self": 12.766352403843484, "children": { "env_step": { "total": 10225.800621895236, "count": 326114, "self": 7687.731230496502, "children": { "SubprocessEnvManager._take_step": { "total": 2530.0224337018954, "count": 326114, "self": 88.52938099942548, "children": { "TorchPolicy.evaluate": { "total": 2441.49305270247, "count": 648226, "self": 2441.49305270247 } } }, "workers": { "total": 8.046957696838945, "count": 326114, "self": 0.0, "children": { "worker_root": { "total": 38656.61478819708, "count": 326114, "is_parallel": true, "self": 32614.825070402832, "children": { "steps_from_proto": { "total": 0.050895599961222615, "count": 50, "is_parallel": true, "self": 0.010485600018000696, "children": { "_process_rank_one_or_two_observation": { "total": 0.04040999994322192, "count": 200, "is_parallel": true, "self": 0.04040999994322192 } } }, "UnityEnvironment.step": { "total": 6041.738822194289, "count": 326114, "is_parallel": true, "self": 349.00733889831463, "children": { "UnityEnvironment._generate_step_input": { "total": 290.9354845034177, "count": 326114, "is_parallel": true, "self": 290.9354845034177 }, "communicator.exchange": { "total": 4304.75070740185, "count": 326114, "is_parallel": true, "self": 4304.75070740185 }, "steps_from_proto": { "total": 1097.0452913907066, "count": 652228, "is_parallel": true, "self": 201.47720989406662, "children": { "_process_rank_one_or_two_observation": { "total": 895.5680814966399, "count": 2608912, "is_parallel": true, "self": 895.5680814966399 } } } } } } } } } } }, "trainer_advance": { "total": 28421.54954580137, "count": 326114, "self": 92.37154580643983, "children": { "process_trajectory": { "total": 3075.171738894889, "count": 326114, "self": 3073.312576894881, "children": { "RLTrainer._checkpoint": { "total": 1.8591620000079274, "count": 10, "self": 1.8591620000079274 } } }, "_update_policy": { "total": 25254.00626110004, "count": 229, "self": 929.723273699703, "children": { "TorchPOCAOptimizer.update": { "total": 24324.282987400336, "count": 6870, "self": 24324.282987400336 } } } } } } }, "trainer_threads": { "total": 1.5999976312741637e-06, "count": 1, "self": 1.5999976312741637e-06 }, "TrainerController._save_models": { "total": 0.18397019999974873, "count": 1, "self": 0.01436200000171084, "children": { "RLTrainer._checkpoint": { "total": 0.1696081999980379, "count": 1, "self": 0.1696081999980379 } } } } } } }