{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.3904533386230469, "min": 1.2882801294326782, "max": 3.295759916305542, "count": 4254 }, "SoccerTwos.Policy.Entropy.sum": { "value": 28609.966796875, "min": 22990.83203125, "max": 129749.3203125, "count": 4254 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 65.86842105263158, "min": 36.64179104477612, "max": 999.0, "count": 4254 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20024.0, "min": 16108.0, "max": 23688.0, "count": 4254 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1798.5105950929037, "min": 1196.1724276268728, "max": 1808.3488403073638, "count": 4234 }, "SoccerTwos.Self-play.ELO.sum": { "value": 273373.6104541214, "min": 2392.3448552537457, "max": 426888.17996287055, "count": 4234 }, "SoccerTwos.Step.mean": { "value": 42539980.0, "min": 9584.0, "max": 42539980.0, "count": 4254 }, "SoccerTwos.Step.sum": { "value": 42539980.0, "min": 9584.0, "max": 42539980.0, "count": 4254 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.007297981530427933, "min": -0.1318093091249466, "max": 0.14496907591819763, "count": 4254 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -1.1019952297210693, "min": -22.664989471435547, "max": 25.69183349609375, "count": 4254 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.009257488884031773, "min": -0.13246512413024902, "max": 0.1429915875196457, "count": 4254 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -1.3978807926177979, "min": -22.66445541381836, "max": 24.496675491333008, "count": 4254 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 4254 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 4254 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.027332449590922982, "min": -0.5148000001907349, "max": 0.43275789681233856, "count": 4254 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -4.12719988822937, "min": -72.5819999575615, "max": 81.03759980201721, "count": 4254 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.027332449590922982, "min": -0.5148000001907349, "max": 0.43275789681233856, "count": 4254 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -4.12719988822937, "min": -72.5819999575615, "max": 81.03759980201721, "count": 4254 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 4254 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 4254 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015053725483206411, "min": 0.009645551359668995, "max": 0.027067770607148607, "count": 2062 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015053725483206411, "min": 0.009645551359668995, "max": 0.027067770607148607, "count": 2062 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09696184222896893, "min": 5.0695771763760905e-05, "max": 0.1337097259859244, "count": 2062 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09696184222896893, "min": 5.0695771763760905e-05, "max": 0.1337097259859244, "count": 2062 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0977091853817304, "min": 4.9487714083322017e-05, "max": 0.1364403041700522, "count": 2062 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0977091853817304, "min": 4.9487714083322017e-05, "max": 0.1364403041700522, "count": 2062 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2062 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2062 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2062 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2062 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2062 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2062 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1676127633", "python_version": "3.9.16 (main, Jan 11 2023, 16:16:36) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\Callum\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-executable/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwosDefaultConfig --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": "1676232193" }, "total": 104561.62148460001, "count": 1, "self": 0.11919050001597498, "children": { "run_training.setup": { "total": 0.07068080000000032, "count": 1, "self": 0.07068080000000032 }, "TrainerController.start_learning": { "total": 104561.4316133, "count": 1, "self": 41.29580159901525, "children": { "TrainerController._reset_env": { "total": 4.89005840011453, "count": 213, "self": 4.89005840011453 }, "TrainerController.advance": { "total": 104515.12929890088, "count": 2934621, "self": 38.06343890228891, "children": { "env_step": { "total": 29829.447548796892, "count": 2934621, "self": 22871.76173659786, "children": { "SubprocessEnvManager._take_step": { "total": 6932.620089999336, "count": 2934621, "self": 235.74638921087262, "children": { "TorchPolicy.evaluate": { "total": 6696.873700788464, "count": 5344686, "self": 6696.873700788464 } } }, "workers": { "total": 25.065722199696395, "count": 2934621, "self": 0.0, "children": { "worker_root": { "total": 104479.36547489322, "count": 2934621, "is_parallel": true, "self": 86214.96817979669, "children": { "steps_from_proto": { "total": 0.25403470002401796, "count": 426, "is_parallel": true, "self": 0.05112310001734088, "children": { "_process_rank_one_or_two_observation": { "total": 0.20291160000667707, "count": 1704, "is_parallel": true, "self": 0.20291160000667707 } } }, "UnityEnvironment.step": { "total": 18264.1432603965, "count": 2934621, "is_parallel": true, "self": 1039.7797430948922, "children": { "UnityEnvironment._generate_step_input": { "total": 808.6158373002427, "count": 2934621, "is_parallel": true, "self": 808.6158373002427 }, "communicator.exchange": { "total": 13298.99854800009, "count": 2934621, "is_parallel": true, "self": 13298.99854800009 }, "steps_from_proto": { "total": 3116.7491320012723, "count": 5869242, "is_parallel": true, "self": 605.8667602067026, "children": { "_process_rank_one_or_two_observation": { "total": 2510.8823717945697, "count": 23476968, "is_parallel": true, "self": 2510.8823717945697 } } } } } } } } } } }, "trainer_advance": { "total": 74647.6183112017, "count": 2934621, "self": 384.4300832960871, "children": { "process_trajectory": { "total": 10519.903524505567, "count": 2934621, "self": 10512.114999605581, "children": { "RLTrainer._checkpoint": { "total": 7.788524899986896, "count": 85, "self": 7.788524899986896 } } }, "_update_policy": { "total": 63743.284703400044, "count": 2063, "self": 4757.272067800135, "children": { "TorchPOCAOptimizer.update": { "total": 58986.01263559991, "count": 61888, "self": 58986.01263559991 } } } } } } }, "trainer_threads": { "total": 1.1999945854768157e-06, "count": 1, "self": 1.1999945854768157e-06 }, "TrainerController._save_models": { "total": 0.11645319999661297, "count": 1, "self": 0.025410699992789887, "children": { "RLTrainer._checkpoint": { "total": 0.09104250000382308, "count": 1, "self": 0.09104250000382308 } } } } } } }