{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.4078967571258545, "min": 2.336456775665283, "max": 3.2956981658935547, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 36214.765625, "min": 9577.05859375, "max": 117577.8828125, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 999.0, "min": 457.375, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19980.0, "min": 14636.0, "max": 25336.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1184.3254499596862, "min": 1182.8205049961612, "max": 1202.8285007396225, "count": 212 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2368.6508999193725, "min": 2365.6410099923223, "max": 16773.913050461364, "count": 212 }, "SoccerTwos.Step.mean": { "value": 4999848.0, "min": 9214.0, "max": 4999848.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999848.0, "min": 9214.0, "max": 4999848.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 3.842867954517715e-05, "min": -0.026026951149106026, "max": 0.008658459410071373, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.0003842868027277291, "min": -0.5077522397041321, "max": 0.1476825624704361, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 3.079942689510062e-05, "min": -0.03120846301317215, "max": 0.00824311189353466, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.000307994254399091, "min": -0.48113206028938293, "max": 0.1527102142572403, "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": 0.0, "min": -0.5204266667366028, "max": 0.24879999671663558, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.0, "min": -8.0, "max": 3.483199954032898, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0, "min": -0.5204266667366028, "max": 0.24879999671663558, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.0, "min": -8.0, "max": 3.483199954032898, "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": 0.016669318967372723, "min": 0.01027831111374932, "max": 0.024426347203552724, "count": 231 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016669318967372723, "min": 0.01027831111374932, "max": 0.024426347203552724, "count": 231 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 2.3704922691436535e-09, "min": 2.0531952804603293e-09, "max": 0.007127757417038083, "count": 231 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 2.3704922691436535e-09, "min": 2.0531952804603293e-09, "max": 0.007127757417038083, "count": 231 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 3.8614038485225896e-09, "min": 2.9535242918043992e-09, "max": 0.007214803419386347, "count": 231 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 3.8614038485225896e-09, "min": 2.9535242918043992e-09, "max": 0.007214803419386347, "count": 231 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 231 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 231 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 231 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 231 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 231 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 231 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1733433264", "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\\Vin\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1733443146" }, "total": 9882.538306800008, "count": 1, "self": 0.2110576000122819, "children": { "run_training.setup": { "total": 0.09844090000842698, "count": 1, "self": 0.09844090000842698 }, "TrainerController.start_learning": { "total": 9882.228808299988, "count": 1, "self": 6.253139402309898, "children": { "TrainerController._reset_env": { "total": 6.14166599989403, "count": 25, "self": 6.14166599989403 }, "TrainerController.advance": { "total": 9869.723774297803, "count": 325174, "self": 5.7240172741003335, "children": { "env_step": { "total": 4915.3196110176505, "count": 325174, "self": 3909.858783112548, "children": { "SubprocessEnvManager._take_step": { "total": 1001.2645763029286, "count": 325174, "self": 34.74585919245146, "children": { "TorchPolicy.evaluate": { "total": 966.5187171104772, "count": 645838, "self": 966.5187171104772 } } }, "workers": { "total": 4.196251602174016, "count": 325174, "self": 0.0, "children": { "worker_root": { "total": 9869.221724097064, "count": 325174, "is_parallel": true, "self": 6800.246078896365, "children": { "steps_from_proto": { "total": 0.04255759992520325, "count": 50, "is_parallel": true, "self": 0.008013800164917484, "children": { "_process_rank_one_or_two_observation": { "total": 0.034543799760285765, "count": 200, "is_parallel": true, "self": 0.034543799760285765 } } }, "UnityEnvironment.step": { "total": 3068.9330876007734, "count": 325174, "is_parallel": true, "self": 158.64112120395293, "children": { "UnityEnvironment._generate_step_input": { "total": 150.8026772031444, "count": 325174, "is_parallel": true, "self": 150.8026772031444 }, "communicator.exchange": { "total": 2214.300309102866, "count": 325174, "is_parallel": true, "self": 2214.300309102866 }, "steps_from_proto": { "total": 545.1889800908102, "count": 650348, "is_parallel": true, "self": 102.10490480728913, "children": { "_process_rank_one_or_two_observation": { "total": 443.0840752835211, "count": 2601392, "is_parallel": true, "self": 443.0840752835211 } } } } } } } } } } }, "trainer_advance": { "total": 4948.680146006052, "count": 325174, "self": 46.98278880442376, "children": { "process_trajectory": { "total": 710.0439638016687, "count": 325174, "self": 708.9349991016497, "children": { "RLTrainer._checkpoint": { "total": 1.108964700018987, "count": 10, "self": 1.108964700018987 } } }, "_update_policy": { "total": 4191.65339339996, "count": 231, "self": 829.2122264000063, "children": { "TorchPOCAOptimizer.update": { "total": 3362.4411669999536, "count": 6933, "self": 3362.4411669999536 } } } } } } }, "trainer_threads": { "total": 1.0999792721122503e-06, "count": 1, "self": 1.0999792721122503e-06 }, "TrainerController._save_models": { "total": 0.1102275000012014, "count": 1, "self": 0.0023566999880131334, "children": { "RLTrainer._checkpoint": { "total": 0.10787080001318827, "count": 1, "self": 0.10787080001318827 } } } } } } }