{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.0262696743011475, "min": 1.9880521297454834, "max": 3.295755624771118, "count": 508 }, "SoccerTwos.Policy.Entropy.sum": { "value": 40784.7578125, "min": 25418.4921875, "max": 120190.4140625, "count": 508 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 47.95192307692308, "min": 39.29032258064516, "max": 999.0, "count": 508 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19948.0, "min": 16120.0, "max": 23200.0, "count": 508 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1515.1394460438003, "min": 1180.6211122271916, "max": 1527.1639885210489, "count": 479 }, "SoccerTwos.Self-play.ELO.sum": { "value": 315149.0047771105, "min": 2361.242224454383, "max": 359637.58795954974, "count": 479 }, "SoccerTwos.Step.mean": { "value": 5079950.0, "min": 9538.0, "max": 5079950.0, "count": 508 }, "SoccerTwos.Step.sum": { "value": 5079950.0, "min": 9538.0, "max": 5079950.0, "count": 508 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.02973540686070919, "min": -0.09560553729534149, "max": 0.2579193115234375, "count": 508 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -6.155229091644287, "min": -23.136539459228516, "max": 35.22888946533203, "count": 508 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.03305745869874954, "min": -0.10276874899864197, "max": 0.2554766535758972, "count": 508 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -6.842893600463867, "min": -24.870037078857422, "max": 36.84461212158203, "count": 508 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 508 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 508 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.14444927777645092, "min": -0.4830588242586921, "max": 0.5767661285015845, "count": 508 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -29.901000499725342, "min": -44.858599841594696, "max": 71.51899993419647, "count": 508 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.14444927777645092, "min": -0.4830588242586921, "max": 0.5767661285015845, "count": 508 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -29.901000499725342, "min": -44.858599841594696, "max": 71.51899993419647, "count": 508 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 508 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 508 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01595897461908559, "min": 0.011230257884350673, "max": 0.023755209202257297, "count": 243 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01595897461908559, "min": 0.011230257884350673, "max": 0.023755209202257297, "count": 243 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10269984404246012, "min": 5.126551354805997e-06, "max": 0.12066958571473757, "count": 243 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10269984404246012, "min": 5.126551354805997e-06, "max": 0.12066958571473757, "count": 243 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.1044114867846171, "min": 6.205549493643048e-06, "max": 0.12275022765000661, "count": 243 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.1044114867846171, "min": 6.205549493643048e-06, "max": 0.12275022765000661, "count": 243 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 243 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 243 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 243 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 243 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 243 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 243 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1720805995", "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\\Ave\\miniconda3\\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": "2.3.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1720818841" }, "total": 12846.315494299983, "count": 1, "self": 0.5742558999918401, "children": { "run_training.setup": { "total": 0.07667410001158714, "count": 1, "self": 0.07667410001158714 }, "TrainerController.start_learning": { "total": 12845.66456429998, "count": 1, "self": 7.43605251115514, "children": { "TrainerController._reset_env": { "total": 6.728150500217453, "count": 24, "self": 6.728150500217453 }, "TrainerController.advance": { "total": 12831.357966088573, "count": 345598, "self": 6.89183339982992, "children": { "env_step": { "total": 5336.416878271382, "count": 345598, "self": 4144.636669692758, "children": { "SubprocessEnvManager._take_step": { "total": 1186.9340458841762, "count": 345598, "self": 39.76811819529394, "children": { "TorchPolicy.evaluate": { "total": 1147.1659276888822, "count": 644612, "self": 1147.1659276888822 } } }, "workers": { "total": 4.8461626944481395, "count": 345597, "self": 0.0, "children": { "worker_root": { "total": 12832.510514082445, "count": 345597, "is_parallel": true, "self": 9581.670501844841, "children": { "steps_from_proto": { "total": 0.04172789986478165, "count": 48, "is_parallel": true, "self": 0.007546900014858693, "children": { "_process_rank_one_or_two_observation": { "total": 0.034180999849922955, "count": 192, "is_parallel": true, "self": 0.034180999849922955 } } }, "UnityEnvironment.step": { "total": 3250.7982843377395, "count": 345597, "is_parallel": true, "self": 171.48967445077142, "children": { "UnityEnvironment._generate_step_input": { "total": 165.6886538043036, "count": 345597, "is_parallel": true, "self": 165.6886538043036 }, "communicator.exchange": { "total": 2352.1890384132275, "count": 345597, "is_parallel": true, "self": 2352.1890384132275 }, "steps_from_proto": { "total": 561.4309176694369, "count": 691194, "is_parallel": true, "self": 102.65535279654432, "children": { "_process_rank_one_or_two_observation": { "total": 458.7755648728926, "count": 2764776, "is_parallel": true, "self": 458.7755648728926 } } } } } } } } } } }, "trainer_advance": { "total": 7488.049254417361, "count": 345597, "self": 57.0236196257174, "children": { "process_trajectory": { "total": 1739.8856363912928, "count": 345597, "self": 1738.662033391418, "children": { "RLTrainer._checkpoint": { "total": 1.2236029998748563, "count": 10, "self": 1.2236029998748563 } } }, "_update_policy": { "total": 5691.139998400351, "count": 244, "self": 846.8035820008372, "children": { "TorchPOCAOptimizer.update": { "total": 4844.336416399514, "count": 7320, "self": 4844.336416399514 } } } } } } }, "trainer_threads": { "total": 1.00000761449337e-06, "count": 1, "self": 1.00000761449337e-06 }, "TrainerController._save_models": { "total": 0.142394200025592, "count": 1, "self": 0.007007400039583445, "children": { "RLTrainer._checkpoint": { "total": 0.13538679998600855, "count": 1, "self": 0.13538679998600855 } } } } } } }