{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.277820587158203, "min": 2.233041763305664, "max": 2.971186637878418, "count": 160 }, "SoccerTwos.Policy.Entropy.sum": { "value": 43588.375, "min": 18071.310546875, "max": 65700.578125, "count": 160 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 75.64615384615385, "min": 52.75555555555555, "max": 156.96875, "count": 160 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19668.0, "min": 2788.0, "max": 21592.0, "count": 160 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1548.0452403303507, "min": 1303.0682328106807, "max": 1560.847477448936, "count": 160 }, "SoccerTwos.Self-play.ELO.sum": { "value": 201245.8812429456, "min": 21029.240688677917, "max": 281108.6245172949, "count": 160 }, "SoccerTwos.Step.mean": { "value": 4999966.0, "min": 3409917.0, "max": 4999966.0, "count": 160 }, "SoccerTwos.Step.sum": { "value": 4999966.0, "min": 3409917.0, "max": 4999966.0, "count": 160 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.07828344404697418, "min": -0.025616463273763657, "max": 0.206451416015625, "count": 160 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 10.176847457885742, "min": -3.7143871784210205, "max": 28.49029541015625, "count": 160 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.07244706898927689, "min": -0.02666577138006687, "max": 0.20727582275867462, "count": 160 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 9.418119430541992, "min": -3.866536855697632, "max": 28.604063034057617, "count": 160 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 160 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 160 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.1599061553294842, "min": -0.2795611106687122, "max": 0.47410973405416035, "count": 160 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 20.787800192832947, "min": -38.73800003528595, "max": 53.57439994812012, "count": 160 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.1599061553294842, "min": -0.2795611106687122, "max": 0.47410973405416035, "count": 160 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 20.787800192832947, "min": -38.73800003528595, "max": 53.57439994812012, "count": 160 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 160 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 160 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016362083276423314, "min": 0.012747406342532486, "max": 0.021592475559252002, "count": 77 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016362083276423314, "min": 0.012747406342532486, "max": 0.021592475559252002, "count": 77 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08703848247726759, "min": 0.043512505541245146, "max": 0.09584195911884308, "count": 77 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.08703848247726759, "min": 0.043512505541245146, "max": 0.09584195911884308, "count": 77 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.08898836001753807, "min": 0.04558493693669637, "max": 0.09694288621346156, "count": 77 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.08898836001753807, "min": 0.04558493693669637, "max": 0.09694288621346156, "count": 77 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 77 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 77 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 77 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 77 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 77 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 77 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1688136081", "python_version": "3.9.16 (main, May 17 2023, 17:49:16) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\gava_\\miniconda3\\envs\\rl_7\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --torch-device=cuda --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cu118", "numpy_version": "1.21.2", "end_time_seconds": "1688139308" }, "total": 3226.9689866, "count": 1, "self": 2.2630827999996654, "children": { "run_training.setup": { "total": 0.1483901999999997, "count": 1, "self": 0.1483901999999997 }, "TrainerController.start_learning": { "total": 3224.5575136, "count": 1, "self": 2.6613024000321275, "children": { "TrainerController._reset_env": { "total": 10.684930699999972, "count": 9, "self": 10.684930699999972 }, "TrainerController.advance": { "total": 3210.9817783999683, "count": 108296, "self": 2.7155326000065543, "children": { "env_step": { "total": 2242.4152754999836, "count": 108296, "self": 1249.9930535000467, "children": { "SubprocessEnvManager._take_step": { "total": 990.8399423999942, "count": 108296, "self": 20.11214710002855, "children": { "TorchPolicy.evaluate": { "total": 970.7277952999657, "count": 199626, "self": 970.7277952999657 } } }, "workers": { "total": 1.5822795999428223, "count": 108296, "self": 0.0, "children": { "worker_root": { "total": 3216.7188293000618, "count": 108296, "is_parallel": true, "self": 2240.770959000104, "children": { "steps_from_proto": { "total": 0.015113399999514332, "count": 18, "is_parallel": true, "self": 0.0031775999996366266, "children": { "_process_rank_one_or_two_observation": { "total": 0.011935799999877705, "count": 72, "is_parallel": true, "self": 0.011935799999877705 } } }, "UnityEnvironment.step": { "total": 975.9327568999579, "count": 108296, "is_parallel": true, "self": 56.801512999965894, "children": { "UnityEnvironment._generate_step_input": { "total": 42.889611400014545, "count": 108296, "is_parallel": true, "self": 42.889611400014545 }, "communicator.exchange": { "total": 705.4799123999802, "count": 108296, "is_parallel": true, "self": 705.4799123999802 }, "steps_from_proto": { "total": 170.76172009999718, "count": 216592, "is_parallel": true, "self": 36.24901950005798, "children": { "_process_rank_one_or_two_observation": { "total": 134.5127005999392, "count": 866368, "is_parallel": true, "self": 134.5127005999392 } } } } } } } } } } }, "trainer_advance": { "total": 965.8509702999783, "count": 108296, "self": 19.738505599945142, "children": { "process_trajectory": { "total": 446.5538022000351, "count": 108296, "self": 445.04256160003484, "children": { "RLTrainer._checkpoint": { "total": 1.5112406000002352, "count": 4, "self": 1.5112406000002352 } } }, "_update_policy": { "total": 499.558662499998, "count": 77, "self": 271.1019353000052, "children": { "TorchPOCAOptimizer.update": { "total": 228.45672719999277, "count": 2310, "self": 228.45672719999277 } } } } } } }, "trainer_threads": { "total": 2.000000222324161e-06, "count": 1, "self": 2.000000222324161e-06 }, "TrainerController._save_models": { "total": 0.22950009999976828, "count": 1, "self": 0.017689499999505642, "children": { "RLTrainer._checkpoint": { "total": 0.21181060000026264, "count": 1, "self": 0.21181060000026264 } } } } } } }