{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": -3.576278402306343e-07, "min": -3.576278402306343e-07, "max": 3.2945072650909424, "count": 3825 }, "SoccerTwos.Policy.Entropy.sum": { "value": -0.00781631376594305, "min": -0.019557951018214226, "max": 167398.328125, "count": 3825 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 720.1428571428571, "min": 285.06666666666666, "max": 999.0, "count": 3825 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20164.0, "min": 3660.0, "max": 28808.0, "count": 3825 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1569.9423849064597, "min": 1530.1366432078805, "max": 1635.3633316190458, "count": 3074 }, "SoccerTwos.Self-play.ELO.sum": { "value": 6279.769539625839, "min": 3060.273286415761, "max": 27767.161065008182, "count": 3074 }, "SoccerTwos.Step.mean": { "value": 49999654.0, "min": 11759873.0, "max": 49999654.0, "count": 3825 }, "SoccerTwos.Step.sum": { "value": 49999654.0, "min": 11759873.0, "max": 49999654.0, "count": 3825 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.009638502262532711, "min": -0.026710689067840576, "max": 0.011438295245170593, "count": 3825 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.1349390298128128, "min": -0.47578129172325134, "max": 0.2820509672164917, "count": 3825 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.009638502262532711, "min": -0.026710689067840576, "max": 0.011438295245170593, "count": 3825 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.1349390298128128, "min": -0.47578129172325134, "max": 0.2820509672164917, "count": 3825 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 3825 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 3825 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.002171431268964495, "min": -0.625, "max": 0.45912940361920523, "count": 3825 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -0.03040003776550293, "min": -12.0, "max": 9.62279999256134, "count": 3825 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.002171431268964495, "min": -0.625, "max": 0.45912940361920523, "count": 3825 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -0.03040003776550293, "min": -12.0, "max": 9.62279999256134, "count": 3825 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3825 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3825 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.005191320995800197, "min": 0.0025595865241484716, "max": 0.0512155355347204, "count": 1754 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.005191320995800197, "min": 0.0025595865241484716, "max": 0.0512155355347204, "count": 1754 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.004174860217608512, "min": 1.987874747866325e-08, "max": 0.009012238495051861, "count": 1754 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.004174860217608512, "min": 1.987874747866325e-08, "max": 0.009012238495051861, "count": 1754 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.004174860217608512, "min": 1.987874747866325e-08, "max": 0.009012238495051861, "count": 1754 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.004174860217608512, "min": 1.987874747866325e-08, "max": 0.009012238495051861, "count": 1754 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1754 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1754 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.2, "min": 0.2, "max": 0.2, "count": 1754 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.2, "min": 0.2, "max": 0.2, "count": 1754 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.004999999999999999, "min": 0.004999999999999999, "max": 0.004999999999999999, "count": 1754 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.004999999999999999, "min": 0.004999999999999999, "max": 0.004999999999999999, "count": 1754 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1694066726", "python_version": "3.9.17 (main, Jul 5 2023, 20:41:20) \n[GCC 11.2.0]", "command_line_arguments": "/home/acm/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./trained-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu113", "numpy_version": "1.21.2", "end_time_seconds": "1694104736" }, "total": 38009.418713622, "count": 1, "self": 0.16675795900664525, "children": { "run_training.setup": { "total": 0.0044328529984341, "count": 1, "self": 0.0044328529984341 }, "TrainerController.start_learning": { "total": 38009.247522809994, "count": 1, "self": 16.779527878439694, "children": { "TrainerController._reset_env": { "total": 12.369896524967771, "count": 192, "self": 12.369896524967771 }, "TrainerController.advance": { "total": 37977.201706746586, "count": 2497504, "self": 17.63627195636218, "children": { "env_step": { "total": 25689.303988712014, "count": 2497504, "self": 20316.80456168284, "children": { "SubprocessEnvManager._take_step": { "total": 5361.335743209242, "count": 2497504, "self": 139.39434876448286, "children": { "TorchPolicy.evaluate": { "total": 5221.941394444759, "count": 4954172, "self": 5221.941394444759 } } }, "workers": { "total": 11.163683819933794, "count": 2497504, "self": 0.0, "children": { "worker_root": { "total": 37940.311905019604, "count": 2497504, "is_parallel": true, "self": 20382.960668171065, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018097739994118456, "count": 2, "is_parallel": true, "self": 0.0003727360090124421, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014370379903994035, "count": 8, "is_parallel": true, "self": 0.0014370379903994035 } } }, "UnityEnvironment.step": { "total": 0.013925006998761091, "count": 1, "is_parallel": true, "self": 0.0004372239964141045, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003484500011836644, "count": 1, "is_parallel": true, "self": 0.0003484500011836644 }, "communicator.exchange": { "total": 0.011721148999640718, "count": 1, "is_parallel": true, "self": 0.011721148999640718 }, "steps_from_proto": { "total": 0.0014181840015226044, "count": 2, "is_parallel": true, "self": 0.00026026300474768505, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011579209967749193, "count": 8, "is_parallel": true, "self": 0.0011579209967749193 } } } } } } }, "steps_from_proto": { "total": 0.26497412007302046, "count": 382, "is_parallel": true, "self": 0.04817248907056637, "children": { "_process_rank_one_or_two_observation": { "total": 0.2168016310024541, "count": 1528, "is_parallel": true, "self": 0.2168016310024541 } } }, "UnityEnvironment.step": { "total": 17557.086262728466, "count": 2497503, "is_parallel": true, "self": 1040.7441306267792, "children": { "UnityEnvironment._generate_step_input": { "total": 696.1562557399302, "count": 2497503, "is_parallel": true, "self": 696.1562557399302 }, "communicator.exchange": { "total": 12537.580525180903, "count": 2497503, "is_parallel": true, "self": 12537.580525180903 }, "steps_from_proto": { "total": 3282.605351180853, "count": 4995006, "is_parallel": true, "self": 520.684407304172, "children": { "_process_rank_one_or_two_observation": { "total": 2761.920943876681, "count": 19980024, "is_parallel": true, "self": 2761.920943876681 } } } } } } } } } } }, "trainer_advance": { "total": 12270.26144607821, "count": 2497504, "self": 223.05618517052426, "children": { "process_trajectory": { "total": 1873.0487656927762, "count": 2497504, "self": 1659.739481237826, "children": { "RLTrainer._checkpoint": { "total": 213.3092844549501, "count": 77, "self": 213.3092844549501 } } }, "_update_policy": { "total": 10174.15649521491, "count": 1754, "self": 4030.5775346320224, "children": { "TorchPOCAOptimizer.update": { "total": 6143.578960582887, "count": 17540, "self": 6143.578960582887 } } } } } } }, "trainer_threads": { "total": 4.00003045797348e-07, "count": 1, "self": 4.00003045797348e-07 }, "TrainerController._save_models": { "total": 2.896391259993834, "count": 1, "self": 0.13090770099370275, "children": { "RLTrainer._checkpoint": { "total": 2.765483559000131, "count": 1, "self": 2.765483559000131 } } } } } } }