{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.6722567081451416, "min": 2.6722567081451416, "max": 3.2956702709198, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 51221.81640625, "min": 20657.2734375, "max": 128743.671875, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 62.64935064935065, "min": 62.1125, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19296.0, "min": 12628.0, "max": 29800.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1355.219331436193, "min": 1162.1279104255987, "max": 1355.219331436193, "count": 370 }, "SoccerTwos.Self-play.ELO.sum": { "value": 208703.77704117371, "min": 2325.8553428847713, "max": 214350.2771818267, "count": 370 }, "SoccerTwos.Step.mean": { "value": 4999996.0, "min": 9916.0, "max": 4999996.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999996.0, "min": 9916.0, "max": 4999996.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.18097859621047974, "min": -0.04156883805990219, "max": 0.18097859621047974, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 27.870704650878906, "min": -5.4455180168151855, "max": 27.870704650878906, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.17801068723201752, "min": -0.033743783831596375, "max": 0.17801068723201752, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 27.413644790649414, "min": -4.420435905456543, "max": 27.413644790649414, "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": 0.24650779211675966, "min": -0.5714285714285714, "max": 0.4190259261263741, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 37.96219998598099, "min": -25.11760026216507, "max": 45.25480002164841, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.24650779211675966, "min": -0.5714285714285714, "max": 0.4190259261263741, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 37.96219998598099, "min": -25.11760026216507, "max": 45.25480002164841, "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": 0.013991575172015776, "min": 0.011833405867704035, "max": 0.02509255342981002, "count": 234 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.013991575172015776, "min": 0.011833405867704035, "max": 0.02509255342981002, "count": 234 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0724312903980414, "min": 3.3134653006546463e-08, "max": 0.07663838565349579, "count": 234 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0724312903980414, "min": 3.3134653006546463e-08, "max": 0.07663838565349579, "count": 234 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.07402855629722277, "min": 1.7340208794773085e-07, "max": 0.07837277377645174, "count": 234 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.07402855629722277, "min": 1.7340208794773085e-07, "max": 0.07837277377645174, "count": 234 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 234 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 234 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 234 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 234 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 234 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 234 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1701015965", "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\\steve\\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": "2.1.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1701027055" }, "total": 11090.048796800023, "count": 1, "self": 2.9569327000062913, "children": { "run_training.setup": { "total": 0.08535220002522692, "count": 1, "self": 0.08535220002522692 }, "TrainerController.start_learning": { "total": 11087.006511899992, "count": 1, "self": 6.914753692573868, "children": { "TrainerController._reset_env": { "total": 5.3145538000098895, "count": 25, "self": 5.3145538000098895 }, "TrainerController.advance": { "total": 11074.606651307404, "count": 326193, "self": 7.225852803676389, "children": { "env_step": { "total": 5100.542327202187, "count": 326193, "self": 3858.400791412423, "children": { "SubprocessEnvManager._take_step": { "total": 1237.867596394819, "count": 326193, "self": 41.47245110152289, "children": { "TorchPolicy.evaluate": { "total": 1196.395145293296, "count": 643228, "self": 1196.395145293296 } } }, "workers": { "total": 4.273939394945046, "count": 326193, "self": 0.0, "children": { "worker_root": { "total": 11073.953368303133, "count": 326193, "is_parallel": true, "self": 8076.754605194554, "children": { "steps_from_proto": { "total": 0.04042590013705194, "count": 50, "is_parallel": true, "self": 0.008597200299846008, "children": { "_process_rank_one_or_two_observation": { "total": 0.03182869983720593, "count": 200, "is_parallel": true, "self": 0.03182869983720593 } } }, "UnityEnvironment.step": { "total": 2997.1583372084424, "count": 326193, "is_parallel": true, "self": 158.60770021527424, "children": { "UnityEnvironment._generate_step_input": { "total": 129.4777721852297, "count": 326193, "is_parallel": true, "self": 129.4777721852297 }, "communicator.exchange": { "total": 2190.4219631002343, "count": 326193, "is_parallel": true, "self": 2190.4219631002343 }, "steps_from_proto": { "total": 518.6509017077042, "count": 652386, "is_parallel": true, "self": 107.77134831435978, "children": { "_process_rank_one_or_two_observation": { "total": 410.8795533933444, "count": 2609544, "is_parallel": true, "self": 410.8795533933444 } } } } } } } } } } }, "trainer_advance": { "total": 5966.83847130154, "count": 326193, "self": 54.590560592274414, "children": { "process_trajectory": { "total": 837.1124061090231, "count": 326193, "self": 835.8342847090389, "children": { "RLTrainer._checkpoint": { "total": 1.2781213999842294, "count": 10, "self": 1.2781213999842294 } } }, "_update_policy": { "total": 5075.135504600243, "count": 234, "self": 662.3041194002144, "children": { "TorchPOCAOptimizer.update": { "total": 4412.831385200028, "count": 7020, "self": 4412.831385200028 } } } } } } }, "trainer_threads": { "total": 8.00006091594696e-07, "count": 1, "self": 8.00006091594696e-07 }, "TrainerController._save_models": { "total": 0.17055229999823496, "count": 1, "self": 0.008953999989898875, "children": { "RLTrainer._checkpoint": { "total": 0.16159830000833608, "count": 1, "self": 0.16159830000833608 } } } } } } }