{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.944350242614746, "min": 1.8522487878799438, "max": 3.295809745788574, "count": 1205 }, "SoccerTwos.Policy.Entropy.sum": { "value": 34469.44140625, "min": 21812.57421875, "max": 143034.546875, "count": 1205 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 111.8, "min": 55.80681818181818, "max": 999.0, "count": 1205 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20124.0, "min": 16280.0, "max": 25064.0, "count": 1205 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1394.7572725208588, "min": 1187.472544095537, "max": 1409.750722353558, "count": 1188 }, "SoccerTwos.Self-play.ELO.sum": { "value": 125528.15452687729, "min": 2377.5087240323387, "max": 239532.3248419899, "count": 1188 }, "SoccerTwos.Step.mean": { "value": 12049992.0, "min": 9552.0, "max": 12049992.0, "count": 1205 }, "SoccerTwos.Step.sum": { "value": 12049992.0, "min": 9552.0, "max": 12049992.0, "count": 1205 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.014131242409348488, "min": -0.13480539619922638, "max": 0.1442411094903946, "count": 1205 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 1.271811842918396, "min": -15.907036781311035, "max": 18.52534294128418, "count": 1205 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.01727334037423134, "min": -0.141114741563797, "max": 0.14866136014461517, "count": 1205 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 1.5546005964279175, "min": -16.651538848876953, "max": 18.110807418823242, "count": 1205 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1205 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1205 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.07812000115712484, "min": -0.5906599998474121, "max": 0.4757999997457554, "count": 1205 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -7.030800104141235, "min": -46.189199805259705, "max": 46.235599637031555, "count": 1205 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.07812000115712484, "min": -0.5906599998474121, "max": 0.4757999997457554, "count": 1205 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -7.030800104141235, "min": -46.189199805259705, "max": 46.235599637031555, "count": 1205 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1205 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1205 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.03365601362214268, "min": 0.0106366954142383, "max": 0.04034976169156532, "count": 579 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.03365601362214268, "min": 0.0106366954142383, "max": 0.04034976169156532, "count": 579 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0651316242913405, "min": 4.619778042069811e-06, "max": 0.07575724944472313, "count": 579 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0651316242913405, "min": 4.619778042069811e-06, "max": 0.07575724944472313, "count": 579 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.06669253632426261, "min": 4.491126583161531e-06, "max": 0.07993168036142985, "count": 579 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.06669253632426261, "min": 4.491126583161531e-06, "max": 0.07993168036142985, "count": 579 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0010000000000000002, "min": 0.0010000000000000002, "max": 0.0010000000000000002, "count": 579 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0010000000000000002, "min": 0.0010000000000000002, "max": 0.0010000000000000002, "count": 579 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 579 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 579 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 579 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 579 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679862293", "python_version": "3.9.16 (main, Mar 8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\yekem\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos-11 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.0+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1679930102" }, "total": 67809.5646884, "count": 1, "self": 0.5156814000074519, "children": { "run_training.setup": { "total": 0.11751230000000001, "count": 1, "self": 0.11751230000000001 }, "TrainerController.start_learning": { "total": 67808.9314947, "count": 1, "self": 24.322138303687098, "children": { "TrainerController._reset_env": { "total": 6.390184500031816, "count": 61, "self": 6.390184500031816 }, "TrainerController.advance": { "total": 67777.99128859627, "count": 805400, "self": 24.743546597353998, "children": { "env_step": { "total": 19152.691756296394, "count": 805400, "self": 14564.122828398626, "children": { "SubprocessEnvManager._take_step": { "total": 4572.911450297158, "count": 805400, "self": 152.57671509764714, "children": { "TorchPolicy.evaluate": { "total": 4420.334735199511, "count": 1522464, "self": 4420.334735199511 } } }, "workers": { "total": 15.657477600610159, "count": 805399, "self": 0.0, "children": { "worker_root": { "total": 67771.78234530085, "count": 805399, "is_parallel": true, "self": 56085.31783019983, "children": { "steps_from_proto": { "total": 0.1635181000134347, "count": 122, "is_parallel": true, "self": 0.030802099968354923, "children": { "_process_rank_one_or_two_observation": { "total": 0.13271600004507977, "count": 488, "is_parallel": true, "self": 0.13271600004507977 } } }, "UnityEnvironment.step": { "total": 11686.30099700101, "count": 805399, "is_parallel": true, "self": 710.1899289980065, "children": { "UnityEnvironment._generate_step_input": { "total": 559.2545161028197, "count": 805399, "is_parallel": true, "self": 559.2545161028197 }, "communicator.exchange": { "total": 8165.148226898103, "count": 805399, "is_parallel": true, "self": 8165.148226898103 }, "steps_from_proto": { "total": 2251.708325002081, "count": 1610798, "is_parallel": true, "self": 424.1858077917934, "children": { "_process_rank_one_or_two_observation": { "total": 1827.5225172102876, "count": 6443192, "is_parallel": true, "self": 1827.5225172102876 } } } } } } } } } } }, "trainer_advance": { "total": 48600.55598570252, "count": 805399, "self": 169.06942730484297, "children": { "process_trajectory": { "total": 4521.3560697977555, "count": 805399, "self": 4515.719589397753, "children": { "RLTrainer._checkpoint": { "total": 5.636480400002256, "count": 24, "self": 5.636480400002256 } } }, "_update_policy": { "total": 43910.13048859993, "count": 579, "self": 2356.6861508001457, "children": { "TorchPOCAOptimizer.update": { "total": 41553.44433779978, "count": 17370, "self": 41553.44433779978 } } } } } } }, "trainer_threads": { "total": 1.7999991541728377e-06, "count": 1, "self": 1.7999991541728377e-06 }, "TrainerController._save_models": { "total": 0.22788150000269525, "count": 1, "self": 0.003679400004330091, "children": { "RLTrainer._checkpoint": { "total": 0.22420209999836516, "count": 1, "self": 0.22420209999836516 } } } } } } }