{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.218026876449585, "min": 3.2003042697906494, "max": 3.2957470417022705, "count": 50 }, "SoccerTwos.Policy.Entropy.sum": { "value": 43662.1875, "min": 30325.921875, "max": 105463.90625, "count": 50 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 963.6, "min": 443.5, "max": 999.0, "count": 50 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19272.0, "min": 16416.0, "max": 25480.0, "count": 50 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1190.5746398791896, "min": 1188.4673514083206, "max": 1199.1445113828395, "count": 43 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2381.149279758379, "min": 2376.934702816641, "max": 14364.40571763741, "count": 43 }, "SoccerTwos.Step.mean": { "value": 499572.0, "min": 9758.0, "max": 499572.0, "count": 50 }, "SoccerTwos.Step.sum": { "value": 499572.0, "min": 9758.0, "max": 499572.0, "count": 50 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.00011170967627549544, "min": -0.0051085129380226135, "max": 0.09762725234031677, "count": 50 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.0011170967482030392, "min": -0.06130215525627136, "max": 1.4644087553024292, "count": 50 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.00048490139306522906, "min": -0.004349739756435156, "max": 0.09764755517244339, "count": 50 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.00484901387244463, "min": -0.05219687893986702, "max": 1.4647133350372314, "count": 50 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 50 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 50 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0, "min": -0.6662666666631897, "max": 0.2737714307648795, "count": 50 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.0, "min": -9.993999999947846, "max": 3.832800030708313, "count": 50 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0, "min": -0.6662666666631897, "max": 0.2737714307648795, "count": 50 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.0, "min": -9.993999999947846, "max": 3.832800030708313, "count": 50 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.018008682879250653, "min": 0.011077817843276232, "max": 0.020610303218321253, "count": 23 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018008682879250653, "min": 0.011077817843276232, "max": 0.020610303218321253, "count": 23 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0008591158400425532, "min": 0.0008100116940719696, "max": 0.006901469205816587, "count": 23 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0008591158400425532, "min": 0.0008100116940719696, "max": 0.006901469205816587, "count": 23 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0008535984105643972, "min": 0.0008109512787389879, "max": 0.006317682222773632, "count": 23 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0008535984105643972, "min": 0.0008109512787389879, "max": 0.006317682222773632, "count": 23 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 23 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 23 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 23 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 23 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 23 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 23 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1711121568", "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\\Computer\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/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+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1711126118" }, "total": 4549.7723790999735, "count": 1, "self": 0.6771422999445349, "children": { "run_training.setup": { "total": 0.37549200002104044, "count": 1, "self": 0.37549200002104044 }, "TrainerController.start_learning": { "total": 4548.719744800008, "count": 1, "self": 1.8136510997428559, "children": { "TrainerController._reset_env": { "total": 13.482682200032286, "count": 3, "self": 13.482682200032286 }, "TrainerController.advance": { "total": 4533.081959500152, "count": 32810, "self": 2.014280197559856, "children": { "env_step": { "total": 1575.299528304895, "count": 32810, "self": 1171.2253187116585, "children": { "SubprocessEnvManager._take_step": { "total": 402.9909484978998, "count": 32810, "self": 11.82861390087055, "children": { "TorchPolicy.evaluate": { "total": 391.16233459702926, "count": 65152, "self": 391.16233459702926 } } }, "workers": { "total": 1.0832610953366384, "count": 32810, "self": 0.0, "children": { "worker_root": { "total": 4534.897381497431, "count": 32810, "is_parallel": true, "self": 3634.059834805026, "children": { "steps_from_proto": { "total": 0.01537760003702715, "count": 6, "is_parallel": true, "self": 0.0033713001757860184, "children": { "_process_rank_one_or_two_observation": { "total": 0.012006299861241132, "count": 24, "is_parallel": true, "self": 0.012006299861241132 } } }, "UnityEnvironment.step": { "total": 900.8221690923674, "count": 32810, "is_parallel": true, "self": 43.885291585174855, "children": { "UnityEnvironment._generate_step_input": { "total": 45.92007690249011, "count": 32810, "is_parallel": true, "self": 45.92007690249011 }, "communicator.exchange": { "total": 660.5651690016384, "count": 32810, "is_parallel": true, "self": 660.5651690016384 }, "steps_from_proto": { "total": 150.45163160306402, "count": 65620, "is_parallel": true, "self": 29.361153592239134, "children": { "_process_rank_one_or_two_observation": { "total": 121.09047801082488, "count": 262480, "is_parallel": true, "self": 121.09047801082488 } } } } } } } } } } }, "trainer_advance": { "total": 2955.7681509976974, "count": 32810, "self": 11.327981101931073, "children": { "process_trajectory": { "total": 368.7541753957048, "count": 32810, "self": 368.10931289568543, "children": { "RLTrainer._checkpoint": { "total": 0.6448625000193715, "count": 1, "self": 0.6448625000193715 } } }, "_update_policy": { "total": 2575.6859945000615, "count": 23, "self": 236.94466579932487, "children": { "TorchPOCAOptimizer.update": { "total": 2338.7413287007366, "count": 690, "self": 2338.7413287007366 } } } } } } }, "trainer_threads": { "total": 4.300032742321491e-06, "count": 1, "self": 4.300032742321491e-06 }, "TrainerController._save_models": { "total": 0.3414477000478655, "count": 1, "self": 0.017190900049172342, "children": { "RLTrainer._checkpoint": { "total": 0.32425679999869317, "count": 1, "self": 0.32425679999869317 } } } } } } }