{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.2742669582366943, "min": 3.2742669582366943, "max": 3.2957334518432617, "count": 10 }, "SoccerTwos.Policy.Entropy.sum": { "value": 70724.1640625, "min": 31687.91015625, "max": 105463.46875, "count": 10 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 769.0, "min": 511.2857142857143, "max": 999.0, "count": 10 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 18456.0, "min": 13296.0, "max": 26752.0, "count": 10 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1196.1531254110819, "min": 1194.8489699455254, "max": 1198.7535925691843, "count": 9 }, "SoccerTwos.Self-play.ELO.sum": { "value": 4784.6125016443275, "min": 2390.1285157180587, "max": 14353.995970830434, "count": 9 }, "SoccerTwos.Step.mean": { "value": 99470.0, "min": 9392.0, "max": 99470.0, "count": 10 }, "SoccerTwos.Step.sum": { "value": 99470.0, "min": 9392.0, "max": 99470.0, "count": 10 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.02711886540055275, "min": 0.026341447606682777, "max": 0.07637666165828705, "count": 10 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.35254526138305664, "min": 0.3221576511859894, "max": 1.2220265865325928, "count": 10 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.028054507449269295, "min": 0.024852896109223366, "max": 0.07641187310218811, "count": 10 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.3647086024284363, "min": 0.3166077733039856, "max": 1.2225899696350098, "count": 10 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 10 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 10 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.07027692061204177, "min": -0.3333333333333333, "max": 0.10254545645280318, "count": 10 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -0.913599967956543, "min": -4.0, "max": 1.128000020980835, "count": 10 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.07027692061204177, "min": -0.3333333333333333, "max": 0.10254545645280318, "count": 10 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -0.913599967956543, "min": -4.0, "max": 1.128000020980835, "count": 10 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.018664041239147385, "min": 0.01638758342790728, "max": 0.019611839847074763, "count": 4 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018664041239147385, "min": 0.01638758342790728, "max": 0.019611839847074763, "count": 4 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0016870414430741221, "min": 0.0003547371425983411, "max": 0.006974872729430596, "count": 4 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0016870414430741221, "min": 0.0003547371425983411, "max": 0.006974872729430596, "count": 4 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0017082204828814914, "min": 0.0003368156564344342, "max": 0.006454419515406092, "count": 4 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0017082204828814914, "min": 0.0003368156564344342, "max": 0.006454419515406092, "count": 4 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 4 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 4 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 4 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 4 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 4 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 4 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679183301", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/linux/SoccerTwos.x86_64 --force --run-id=SoccerTwos --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1679183878" }, "total": 577.3796814949999, "count": 1, "self": 0.5908887079999658, "children": { "run_training.setup": { "total": 0.23541098400005467, "count": 1, "self": 0.23541098400005467 }, "TrainerController.start_learning": { "total": 576.5533818029999, "count": 1, "self": 0.2583465830093701, "children": { "TrainerController._reset_env": { "total": 4.048359729999902, "count": 1, "self": 4.048359729999902 }, "TrainerController.advance": { "total": 571.9471983179906, "count": 6698, "self": 0.3294751819823887, "children": { "env_step": { "total": 237.9910622950017, "count": 6698, "self": 194.1527566540069, "children": { "SubprocessEnvManager._take_step": { "total": 43.66683541899806, "count": 6698, "self": 2.1031760379812567, "children": { "TorchPolicy.evaluate": { "total": 41.563659381016805, "count": 13330, "self": 41.563659381016805 } } }, "workers": { "total": 0.1714702219967421, "count": 6698, "self": 0.0, "children": { "worker_root": { "total": 574.9202399819994, "count": 6698, "is_parallel": true, "self": 413.53883929999733, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003467670999953043, "count": 2, "is_parallel": true, "self": 0.0009530439999707596, "children": { "_process_rank_one_or_two_observation": { "total": 0.0025146269999822835, "count": 8, "is_parallel": true, "self": 0.0025146269999822835 } } }, "UnityEnvironment.step": { "total": 0.048476614000037443, "count": 1, "is_parallel": true, "self": 0.001243397000052937, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000938368999868544, "count": 1, "is_parallel": true, "self": 0.000938368999868544 }, "communicator.exchange": { "total": 0.0423584480001864, "count": 1, "is_parallel": true, "self": 0.0423584480001864 }, "steps_from_proto": { "total": 0.003936399999929563, "count": 2, "is_parallel": true, "self": 0.0007509889996981656, "children": { "_process_rank_one_or_two_observation": { "total": 0.0031854110002313973, "count": 8, "is_parallel": true, "self": 0.0031854110002313973 } } } } } } }, "UnityEnvironment.step": { "total": 161.3814006820021, "count": 6697, "is_parallel": true, "self": 8.919849462980665, "children": { "UnityEnvironment._generate_step_input": { "total": 5.479749618011738, "count": 6697, "is_parallel": true, "self": 5.479749618011738 }, "communicator.exchange": { "total": 118.77992843600305, "count": 6697, "is_parallel": true, "self": 118.77992843600305 }, "steps_from_proto": { "total": 28.201873165006646, "count": 13394, "is_parallel": true, "self": 5.430200891993991, "children": { "_process_rank_one_or_two_observation": { "total": 22.771672273012655, "count": 53576, "is_parallel": true, "self": 22.771672273012655 } } } } } } } } } } }, "trainer_advance": { "total": 333.62666084100647, "count": 6698, "self": 2.1063119210039076, "children": { "process_trajectory": { "total": 43.91635050900254, "count": 6698, "self": 43.91635050900254 }, "_update_policy": { "total": 287.603998411, "count": 4, "self": 21.843839609997985, "children": { "TorchPOCAOptimizer.update": { "total": 265.76015880100204, "count": 123, "self": 265.76015880100204 } } } } } } }, "trainer_threads": { "total": 1.76799994733301e-06, "count": 1, "self": 1.76799994733301e-06 }, "TrainerController._save_models": { "total": 0.2994754040000771, "count": 1, "self": 0.0025718780000261177, "children": { "RLTrainer._checkpoint": { "total": 0.296903526000051, "count": 1, "self": 0.296903526000051 } } } } } } }