{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.2625930309295654, "min": 1.2319058179855347, "max": 3.295703887939453, "count": 10000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 25736.6953125, "min": 7288.97705078125, "max": 166827.9375, "count": 10000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 61.1875, "min": 36.223880597014926, "max": 999.0, "count": 10000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19580.0, "min": 14984.0, "max": 25496.0, "count": 10000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1936.4052793693022, "min": 1179.9701896111849, "max": 1954.6093288519044, "count": 9954 }, "SoccerTwos.Self-play.ELO.sum": { "value": 309824.84469908837, "min": 2360.5428694610014, "max": 420712.78266469005, "count": 9954 }, "SoccerTwos.Step.mean": { "value": 99999915.0, "min": 9766.0, "max": 99999915.0, "count": 10000 }, "SoccerTwos.Step.sum": { "value": 99999915.0, "min": 9766.0, "max": 99999915.0, "count": 10000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.05761217325925827, "min": -0.15084847807884216, "max": 0.18576471507549286, "count": 10000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -9.217947959899902, "min": -27.984363555908203, "max": 30.502899169921875, "count": 10000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.05771877244114876, "min": -0.15320295095443726, "max": 0.1849619299173355, "count": 10000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -9.235003471374512, "min": -29.192466735839844, "max": 31.73279571533203, "count": 10000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 10000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 10000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.06525874771177768, "min": -0.6, "max": 0.4652444389131334, "count": 10000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -10.44139963388443, "min": -67.46719998121262, "max": 58.85200011730194, "count": 10000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.06525874771177768, "min": -0.6, "max": 0.4652444389131334, "count": 10000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -10.44139963388443, "min": -67.46719998121262, "max": 58.85200011730194, "count": 10000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01891916963310602, "min": 0.008988662293025603, "max": 0.027234322484582664, "count": 4845 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01891916963310602, "min": 0.008988662293025603, "max": 0.027234322484582664, "count": 4845 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0843171551823616, "min": 6.489815073488595e-07, "max": 0.12778042231996853, "count": 4845 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0843171551823616, "min": 6.489815073488595e-07, "max": 0.12778042231996853, "count": 4845 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.08474663123488427, "min": 6.709530699329964e-07, "max": 0.13118780155976614, "count": 4845 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.08474663123488427, "min": 6.709530699329964e-07, "max": 0.13118780155976614, "count": 4845 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 4845 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 4845 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 4845 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 4845 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 4845 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 4845 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1676296487", "python_version": "3.9.16 (main, Jan 11 2023, 16:16:36) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\fgmck\\miniconda3\\envs\\aivsai\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos_10m --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": "1676576187" }, "total": 279694.5966808, "count": 1, "self": 2.13929400005145, "children": { "run_training.setup": { "total": 0.05586239999999987, "count": 1, "self": 0.05586239999999987 }, "TrainerController.start_learning": { "total": 279692.4015244, "count": 1, "self": 104.30203850875841, "children": { "TrainerController._reset_env": { "total": 18.42813899983614, "count": 500, "self": 18.42813899983614 }, "TrainerController.advance": { "total": 279569.59054319136, "count": 6845160, "self": 108.02706568053691, "children": { "env_step": { "total": 69681.39402179586, "count": 6845160, "self": 53948.19957078957, "children": { "SubprocessEnvManager._take_step": { "total": 15671.696985415652, "count": 6845160, "self": 583.2796191043562, "children": { "TorchPolicy.evaluate": { "total": 15088.417366311296, "count": 12568572, "self": 15088.417366311296 } } }, "workers": { "total": 61.49746559063926, "count": 6845160, "self": 0.0, "children": { "worker_root": { "total": 279532.60969353415, "count": 6845160, "is_parallel": true, "self": 235872.28872201213, "children": { "steps_from_proto": { "total": 0.49677500013222087, "count": 1000, "is_parallel": true, "self": 0.1024867002124612, "children": { "_process_rank_one_or_two_observation": { "total": 0.39428829991975967, "count": 4000, "is_parallel": true, "self": 0.39428829991975967 } } }, "UnityEnvironment.step": { "total": 43659.824196521884, "count": 6845160, "is_parallel": true, "self": 2191.5926055340387, "children": { "UnityEnvironment._generate_step_input": { "total": 1587.0473586041321, "count": 6845160, "is_parallel": true, "self": 1587.0473586041321 }, "communicator.exchange": { "total": 33092.21876747363, "count": 6845160, "is_parallel": true, "self": 33092.21876747363 }, "steps_from_proto": { "total": 6788.965464910085, "count": 13690320, "is_parallel": true, "self": 1406.7760745736396, "children": { "_process_rank_one_or_two_observation": { "total": 5382.189390336445, "count": 54761280, "is_parallel": true, "self": 5382.189390336445 } } } } } } } } } } }, "trainer_advance": { "total": 209780.169455715, "count": 6845160, "self": 726.6273992492934, "children": { "process_trajectory": { "total": 20545.49392576491, "count": 6845160, "self": 20528.705387765345, "children": { "RLTrainer._checkpoint": { "total": 16.7885379995638, "count": 200, "self": 16.7885379995638 } } }, "_update_policy": { "total": 188508.04813070077, "count": 4845, "self": 9791.01684711044, "children": { "TorchPOCAOptimizer.update": { "total": 178717.03128359033, "count": 145350, "self": 178717.03128359033 } } } } } } }, "trainer_threads": { "total": 5.00003807246685e-07, "count": 1, "self": 5.00003807246685e-07 }, "TrainerController._save_models": { "total": 0.08080320002045482, "count": 1, "self": 0.005734700011089444, "children": { "RLTrainer._checkpoint": { "total": 0.07506850000936538, "count": 1, "self": 0.07506850000936538 } } } } } } }