{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.372818112373352, "min": 1.3610069751739502, "max": 3.295746088027954, "count": 2406 }, "SoccerTwos.Policy.Entropy.sum": { "value": 27544.22265625, "min": 13481.908203125, "max": 116511.125, "count": 2406 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 44.28181818181818, "min": 40.8235294117647, "max": 999.0, "count": 2406 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19484.0, "min": 16780.0, "max": 23440.0, "count": 2406 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1616.2424260396367, "min": 1190.5438488044906, "max": 1685.6915875872412, "count": 2386 }, "SoccerTwos.Self-play.ELO.sum": { "value": 355573.3337287201, "min": 2384.762442138258, "max": 374386.6988585349, "count": 2386 }, "SoccerTwos.Step.mean": { "value": 24059983.0, "min": 9422.0, "max": 24059983.0, "count": 2406 }, "SoccerTwos.Step.sum": { "value": 24059983.0, "min": 9422.0, "max": 24059983.0, "count": 2406 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.044170547276735306, "min": -0.1438433974981308, "max": 0.1603071093559265, "count": 2406 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -9.761691093444824, "min": -24.165691375732422, "max": 30.29804229736328, "count": 2406 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.04460342600941658, "min": -0.146144837141037, "max": 0.16351306438446045, "count": 2406 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -9.857357025146484, "min": -24.55233383178711, "max": 30.903968811035156, "count": 2406 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2406 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2406 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.11660633529473215, "min": -0.5490857149873462, "max": 0.45455000166957443, "count": 2406 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -25.770000100135803, "min": -57.58159965276718, "max": 67.27340024709702, "count": 2406 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.11660633529473215, "min": -0.5490857149873462, "max": 0.45455000166957443, "count": 2406 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -25.770000100135803, "min": -57.58159965276718, "max": 67.27340024709702, "count": 2406 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2406 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2406 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.019324933231109752, "min": 0.010011145524913445, "max": 0.02468691694860657, "count": 1163 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.019324933231109752, "min": 0.010011145524913445, "max": 0.02468691694860657, "count": 1163 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.1097671389579773, "min": 4.830325057506949e-05, "max": 0.1255221885939439, "count": 1163 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.1097671389579773, "min": 4.830325057506949e-05, "max": 0.1255221885939439, "count": 1163 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11143294448653857, "min": 4.8788184418905685e-05, "max": 0.12767568851510683, "count": 1163 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11143294448653857, "min": 4.8788184418905685e-05, "max": 0.12767568851510683, "count": 1163 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1163 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1163 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 1163 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 1163 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 1163 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 1163 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1696684423", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/calle/mambaforge/envs/rl/bin/mlagents-learn config/poca/SoccerTwos.yaml --env training-envs-executables/SoccerTwos.x86_64 --run-id SoccerTwos --no-graphics --force", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu121", "numpy_version": "1.21.2", "end_time_seconds": "1696753741" }, "total": 69317.840842983, "count": 1, "self": 4.200484507993679, "children": { "run_training.setup": { "total": 0.027740798999730032, "count": 1, "self": 0.027740798999730032 }, "TrainerController.start_learning": { "total": 69313.612617676, "count": 1, "self": 38.41506820991344, "children": { "TrainerController._reset_env": { "total": 7.527282390986329, "count": 121, "self": 7.527282390986329 }, "TrainerController.advance": { "total": 69267.21945307309, "count": 1659962, "self": 41.54071615994326, "children": { "env_step": { "total": 53528.12489961531, "count": 1659962, "self": 37496.70817228866, "children": { "SubprocessEnvManager._take_step": { "total": 16008.018884459463, "count": 1659962, "self": 315.22460969659915, "children": { "TorchPolicy.evaluate": { "total": 15692.794274762864, "count": 3027070, "self": 15692.794274762864 } } }, "workers": { "total": 23.397842867188956, "count": 1659962, "self": 0.0, "children": { "worker_root": { "total": 69216.53500549789, "count": 1659962, "is_parallel": true, "self": 36265.40393812658, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004964599999766506, "count": 2, "is_parallel": true, "self": 0.0016121999997267267, "children": { "_process_rank_one_or_two_observation": { "total": 0.003352400000039779, "count": 8, "is_parallel": true, "self": 0.003352400000039779 } } }, "UnityEnvironment.step": { "total": 0.051478497999596584, "count": 1, "is_parallel": true, "self": 0.001723199999105418, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004969999999957508, "count": 1, "is_parallel": true, "self": 0.0004969999999957508 }, "communicator.exchange": { "total": 0.044944899000256555, "count": 1, "is_parallel": true, "self": 0.044944899000256555 }, "steps_from_proto": { "total": 0.00431339900023886, "count": 2, "is_parallel": true, "self": 0.00090240000099584, "children": { "_process_rank_one_or_two_observation": { "total": 0.00341099899924302, "count": 8, "is_parallel": true, "self": 0.00341099899924302 } } } } } } }, "UnityEnvironment.step": { "total": 32950.86803147133, "count": 1659961, "is_parallel": true, "self": 1041.6733843843394, "children": { "UnityEnvironment._generate_step_input": { "total": 700.0652687746642, "count": 1659961, "is_parallel": true, "self": 700.0652687746642 }, "communicator.exchange": { "total": 27563.45005935148, "count": 1659961, "is_parallel": true, "self": 27563.45005935148 }, "steps_from_proto": { "total": 3645.679318960845, "count": 3319922, "is_parallel": true, "self": 775.0794357809136, "children": { "_process_rank_one_or_two_observation": { "total": 2870.5998831799316, "count": 13279688, "is_parallel": true, "self": 2870.5998831799316 } } } } }, "steps_from_proto": { "total": 0.263035899980423, "count": 240, "is_parallel": true, "self": 0.05318589999569667, "children": { "_process_rank_one_or_two_observation": { "total": 0.2098499999847263, "count": 960, "is_parallel": true, "self": 0.2098499999847263 } } } } } } } } }, "trainer_advance": { "total": 15697.553837297839, "count": 1659962, "self": 277.09851129868, "children": { "process_trajectory": { "total": 7099.193064037109, "count": 1659962, "self": 7080.448951666099, "children": { "RLTrainer._checkpoint": { "total": 18.744112371010488, "count": 48, "self": 18.744112371010488 } } }, "_update_policy": { "total": 8321.262261962049, "count": 1164, "self": 4029.9179502190127, "children": { "TorchPOCAOptimizer.update": { "total": 4291.344311743036, "count": 34920, "self": 4291.344311743036 } } } } } } }, "trainer_threads": { "total": 1.00000761449337e-06, "count": 1, "self": 1.00000761449337e-06 }, "TrainerController._save_models": { "total": 0.45081300199672114, "count": 1, "self": 0.012058000997058116, "children": { "RLTrainer._checkpoint": { "total": 0.438755000999663, "count": 1, "self": 0.438755000999663 } } } } } } }