{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.2031166553497314, "min": 3.1743788719177246, "max": 3.2957444190979004, "count": 50 }, "SoccerTwos.Policy.Entropy.sum": { "value": 74004.8046875, "min": 35526.40625, "max": 105463.765625, "count": 50 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 787.7142857142857, "min": 570.2222222222222, "max": 999.0, "count": 50 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 22056.0, "min": 14092.0, "max": 26652.0, "count": 50 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1201.2296752739044, "min": 1199.4207269131573, "max": 1202.9898225192671, "count": 28 }, "SoccerTwos.Self-play.ELO.sum": { "value": 4804.9187010956175, "min": 2399.993869418938, "max": 9606.572001020753, "count": 28 }, "SoccerTwos.Step.mean": { "value": 499112.0, "min": 9342.0, "max": 499112.0, "count": 50 }, "SoccerTwos.Step.sum": { "value": 499112.0, "min": 9342.0, "max": 499112.0, "count": 50 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0008938495302572846, "min": -0.06058163940906525, "max": 0.020456980913877487, "count": 50 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.011620043776929379, "min": -0.9086313247680664, "max": 0.22502678632736206, "count": 50 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0009265076369047165, "min": -0.06060228869318962, "max": 0.019780248403549194, "count": 50 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.012044599279761314, "min": -0.9088144898414612, "max": 0.21758273243904114, "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": 0.22747691778036264, "min": -0.5, "max": 0.22747691778036264, "count": 50 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 2.9571999311447144, "min": -7.0, "max": 2.9571999311447144, "count": 50 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.22747691778036264, "min": -0.5, "max": 0.22747691778036264, "count": 50 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 2.9571999311447144, "min": -7.0, "max": 2.9571999311447144, "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": 0.01847975027631037, "min": 0.012878362846095115, "max": 0.021673670453795542, "count": 22 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01847975027631037, "min": 0.012878362846095115, "max": 0.021673670453795542, "count": 22 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 1.8271612437577764e-06, "min": 1.8271612437577764e-06, "max": 0.0038709439492474, "count": 22 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 1.8271612437577764e-06, "min": 1.8271612437577764e-06, "max": 0.0038709439492474, "count": 22 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 1.7986885552545572e-06, "min": 1.7986885552545572e-06, "max": 0.003906380175612867, "count": 22 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 1.7986885552545572e-06, "min": 1.7986885552545572e-06, "max": 0.003906380175612867, "count": 22 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 22 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 22 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 22 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 22 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 22 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 22 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1687006136", "python_version": "3.9.13 (main, Aug 25 2022, 23:51:50) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\Serkanburakors\\Anaconda3\\Scripts\\mlagents-learn C:/Users/Serkanburakors/Desktop/config/poca/SoccerTwos.yaml --env=C:/Users/Serkanburakors/Desktop/training-envs-executables/SoccerTwos.exe --run-id=SoccerTwosv2 --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": "1687008389" }, "total": 2253.4526732, "count": 1, "self": 0.5240215999997417, "children": { "run_training.setup": { "total": 0.30068370000000044, "count": 1, "self": 0.30068370000000044 }, "TrainerController.start_learning": { "total": 2252.6279679000004, "count": 1, "self": 1.144069900033628, "children": { "TrainerController._reset_env": { "total": 10.546699800000086, "count": 3, "self": 10.546699800000086 }, "TrainerController.advance": { "total": 2240.6789963999668, "count": 32707, "self": 1.235399999980018, "children": { "env_step": { "total": 919.8941794999957, "count": 32707, "self": 722.4491024000351, "children": { "SubprocessEnvManager._take_step": { "total": 196.70435049998446, "count": 32707, "self": 7.3281165999748055, "children": { "TorchPolicy.evaluate": { "total": 189.37623390000965, "count": 64992, "self": 189.37623390000965 } } }, "workers": { "total": 0.7407265999762132, "count": 32707, "self": 0.0, "children": { "worker_root": { "total": 2240.234548199997, "count": 32707, "is_parallel": true, "self": 1664.074176300011, "children": { "steps_from_proto": { "total": 0.006901100000106908, "count": 6, "is_parallel": true, "self": 0.0013291999997377957, "children": { "_process_rank_one_or_two_observation": { "total": 0.005571900000369112, "count": 24, "is_parallel": true, "self": 0.005571900000369112 } } }, "UnityEnvironment.step": { "total": 576.1534707999858, "count": 32707, "is_parallel": true, "self": 29.70352360001334, "children": { "UnityEnvironment._generate_step_input": { "total": 22.964788899988697, "count": 32707, "is_parallel": true, "self": 22.964788899988697 }, "communicator.exchange": { "total": 428.0875970000008, "count": 32707, "is_parallel": true, "self": 428.0875970000008 }, "steps_from_proto": { "total": 95.39756129998301, "count": 65414, "is_parallel": true, "self": 19.795588499961298, "children": { "_process_rank_one_or_two_observation": { "total": 75.60197280002171, "count": 261656, "is_parallel": true, "self": 75.60197280002171 } } } } } } } } } } }, "trainer_advance": { "total": 1319.5494168999912, "count": 32707, "self": 8.360698199996477, "children": { "process_trajectory": { "total": 179.74316519999513, "count": 32707, "self": 179.45227349999516, "children": { "RLTrainer._checkpoint": { "total": 0.29089169999997466, "count": 1, "self": 0.29089169999997466 } } }, "_update_policy": { "total": 1131.4455534999995, "count": 22, "self": 105.51229480000006, "children": { "TorchPOCAOptimizer.update": { "total": 1025.9332586999994, "count": 666, "self": 1025.9332586999994 } } } } } } }, "TrainerController._save_models": { "total": 0.2582017999998243, "count": 1, "self": 4.129999979340937e-05, "children": { "RLTrainer._checkpoint": { "total": 0.2581605000000309, "count": 1, "self": 0.2581605000000309 } } } } } } }