{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.904728651046753, "min": 1.8506577014923096, "max": 3.295701503753662, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 37546.01171875, "min": 14177.96484375, "max": 130773.28125, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 70.0, "min": 37.49230769230769, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19880.0, "min": 16212.0, "max": 23652.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1610.7610266624235, "min": 1202.3052571940093, "max": 1611.1401450931248, "count": 495 }, "SoccerTwos.Self-play.ELO.sum": { "value": 228728.06578606414, "min": 2413.5701353887225, "max": 387799.9827319372, "count": 495 }, "SoccerTwos.Step.mean": { "value": 4999998.0, "min": 9030.0, "max": 4999998.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999998.0, "min": 9030.0, "max": 4999998.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0025095499586313963, "min": -0.08400537818670273, "max": 0.17201215028762817, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.35384654998779297, "min": -16.277118682861328, "max": 27.767690658569336, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0030053879600018263, "min": -0.08430910110473633, "max": 0.17198973894119263, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.42375969886779785, "min": -15.025320053100586, "max": 27.629457473754883, "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": -0.05678439647593397, "min": -0.5462799966335297, "max": 0.44480000314165336, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -8.00659990310669, "min": -47.8956001996994, "max": 56.047400057315826, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.05678439647593397, "min": -0.5462799966335297, "max": 0.44480000314165336, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -8.00659990310669, "min": -47.8956001996994, "max": 56.047400057315826, "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": 0.018534475660756774, "min": 0.01142779259001448, "max": 0.028547672267692784, "count": 241 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018534475660756774, "min": 0.01142779259001448, "max": 0.028547672267692784, "count": 241 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0974157584210237, "min": 0.000931472180915686, "max": 0.1241871953010559, "count": 241 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0974157584210237, "min": 0.000931472180915686, "max": 0.1241871953010559, "count": 241 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09848379567265511, "min": 0.0009322931223626559, "max": 0.12728464975953102, "count": 241 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09848379567265511, "min": 0.0009322931223626559, "max": 0.12728464975953102, "count": 241 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 241 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 241 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 241 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 241 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 241 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 241 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675705406", "python_version": "3.9.16 (main, Jan 11 2023, 16:16:36) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\paperspace\\miniconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwosV3 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.13.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1675719321" }, "total": 13914.5420648, "count": 1, "self": 0.2545884000010119, "children": { "run_training.setup": { "total": 0.09392030000000018, "count": 1, "self": 0.09392030000000018 }, "TrainerController.start_learning": { "total": 13914.1935561, "count": 1, "self": 7.957616199984841, "children": { "TrainerController._reset_env": { "total": 4.019166299997285, "count": 25, "self": 4.019166299997285 }, "TrainerController.advance": { "total": 13902.083278300019, "count": 343552, "self": 7.558167800010779, "children": { "env_step": { "total": 5666.114875299987, "count": 343552, "self": 4606.377788799868, "children": { "SubprocessEnvManager._take_step": { "total": 1055.0909048000776, "count": 343552, "self": 41.26710340049283, "children": { "TorchPolicy.evaluate": { "total": 1013.8238013995848, "count": 629886, "self": 1013.8238013995848 } } }, "workers": { "total": 4.646181700041403, "count": 343552, "self": 0.0, "children": { "worker_root": { "total": 13898.14573649977, "count": 343552, "is_parallel": true, "self": 10121.544544700058, "children": { "steps_from_proto": { "total": 0.03868940000534016, "count": 50, "is_parallel": true, "self": 0.008047100007024799, "children": { "_process_rank_one_or_two_observation": { "total": 0.03064229999831536, "count": 200, "is_parallel": true, "self": 0.03064229999831536 } } }, "UnityEnvironment.step": { "total": 3776.562502399706, "count": 343552, "is_parallel": true, "self": 158.93165549989635, "children": { "UnityEnvironment._generate_step_input": { "total": 118.51616079997808, "count": 343552, "is_parallel": true, "self": 118.51616079997808 }, "communicator.exchange": { "total": 3020.8293958996646, "count": 343552, "is_parallel": true, "self": 3020.8293958996646 }, "steps_from_proto": { "total": 478.28529020016686, "count": 687104, "is_parallel": true, "self": 97.97731250005751, "children": { "_process_rank_one_or_two_observation": { "total": 380.30797770010935, "count": 2748416, "is_parallel": true, "self": 380.30797770010935 } } } } } } } } } } }, "trainer_advance": { "total": 8228.41023520002, "count": 343552, "self": 63.70748739979172, "children": { "process_trajectory": { "total": 1252.8230386002326, "count": 343552, "self": 1251.5467199002326, "children": { "RLTrainer._checkpoint": { "total": 1.276318700000047, "count": 10, "self": 1.276318700000047 } } }, "_update_policy": { "total": 6911.879709199997, "count": 241, "self": 803.4124982000103, "children": { "TorchPOCAOptimizer.update": { "total": 6108.4672109999865, "count": 7230, "self": 6108.4672109999865 } } } } } } }, "trainer_threads": { "total": 6.999998731771484e-07, "count": 1, "self": 6.999998731771484e-07 }, "TrainerController._save_models": { "total": 0.1334945999988122, "count": 1, "self": 0.007632799999555573, "children": { "RLTrainer._checkpoint": { "total": 0.12586179999925662, "count": 1, "self": 0.12586179999925662 } } } } } } }