{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.4285483360290527, "min": 2.4123215675354004, "max": 3.295747995376587, "count": 572 }, "SoccerTwos.Policy.Entropy.sum": { "value": 46938.984375, "min": 18835.41796875, "max": 148510.625, "count": 572 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 53.03333333333333, "min": 44.24770642201835, "max": 999.0, "count": 572 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19092.0, "min": 16184.0, "max": 23856.0, "count": 572 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1459.89320978207, "min": 1182.3895751875943, "max": 1463.7659452196, "count": 414 }, "SoccerTwos.Self-play.ELO.sum": { "value": 262780.7777607726, "min": 2365.104459575471, "max": 318731.5104809692, "count": 414 }, "SoccerTwos.Step.mean": { "value": 5719955.0, "min": 9944.0, "max": 5719955.0, "count": 572 }, "SoccerTwos.Step.sum": { "value": 5719955.0, "min": 9944.0, "max": 5719955.0, "count": 572 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0042080082930624485, "min": -0.060339827090501785, "max": 0.17207317054271698, "count": 572 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.761649489402771, "min": -10.137090682983398, "max": 28.5672664642334, "count": 572 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.013848502188920975, "min": -0.06162046268582344, "max": 0.1689547300338745, "count": 572 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -2.5065789222717285, "min": -10.352237701416016, "max": 28.553348541259766, "count": 572 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 572 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 572 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.03215469708100208, "min": -0.5, "max": 0.5003499984741211, "count": 572 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 5.820000171661377, "min": -37.40279978513718, "max": 40.02560031414032, "count": 572 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.03215469708100208, "min": -0.5, "max": 0.5003499984741211, "count": 572 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 5.820000171661377, "min": -37.40279978513718, "max": 40.02560031414032, "count": 572 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 572 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 572 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.013975370206753723, "min": 0.01113784731811999, "max": 0.02317632376604403, "count": 267 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.013975370206753723, "min": 0.01113784731811999, "max": 0.02317632376604403, "count": 267 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10773070926467578, "min": 6.605348067031021e-08, "max": 0.10773070926467578, "count": 267 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10773070926467578, "min": 6.605348067031021e-08, "max": 0.10773070926467578, "count": 267 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.1098634255429109, "min": 6.81121953505226e-08, "max": 0.1098634255429109, "count": 267 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.1098634255429109, "min": 6.81121953505226e-08, "max": 0.1098634255429109, "count": 267 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 267 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 267 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 267 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 267 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 267 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 267 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1701112940", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/gerard/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701128321" }, "total": 15380.66373492, "count": 1, "self": 0.03863696200096456, "children": { "run_training.setup": { "total": 0.01112268499991842, "count": 1, "self": 0.01112268499991842 }, "TrainerController.start_learning": { "total": 15380.613975272998, "count": 1, "self": 8.447987040233784, "children": { "TrainerController._reset_env": { "total": 2.77713225499906, "count": 29, "self": 2.77713225499906 }, "TrainerController.advance": { "total": 15369.187369838766, "count": 376159, "self": 8.412951710271955, "children": { "env_step": { "total": 7363.122731359546, "count": 376159, "self": 5943.645075474607, "children": { "SubprocessEnvManager._take_step": { "total": 1413.947692581413, "count": 376159, "self": 46.85850683716876, "children": { "TorchPolicy.evaluate": { "total": 1367.0891857442443, "count": 732332, "self": 1367.0891857442443 } } }, "workers": { "total": 5.529963303525619, "count": 376159, "self": 0.0, "children": { "worker_root": { "total": 15348.942659730743, "count": 376159, "is_parallel": true, "self": 10437.356349070564, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0025318650000372145, "count": 2, "is_parallel": true, "self": 0.0011279999998805579, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014038650001566566, "count": 8, "is_parallel": true, "self": 0.0014038650001566566 } } }, "UnityEnvironment.step": { "total": 0.027527491000000737, "count": 1, "is_parallel": true, "self": 0.0008405670002957777, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006389699999544973, "count": 1, "is_parallel": true, "self": 0.0006389699999544973 }, "communicator.exchange": { "total": 0.023571671999889077, "count": 1, "is_parallel": true, "self": 0.023571671999889077 }, "steps_from_proto": { "total": 0.002476281999861385, "count": 2, "is_parallel": true, "self": 0.0004359760002898838, "children": { "_process_rank_one_or_two_observation": { "total": 0.002040305999571501, "count": 8, "is_parallel": true, "self": 0.002040305999571501 } } } } } } }, "UnityEnvironment.step": { "total": 4911.523292744176, "count": 376158, "is_parallel": true, "self": 300.24126463963603, "children": { "UnityEnvironment._generate_step_input": { "total": 215.83150862467664, "count": 376158, "is_parallel": true, "self": 215.83150862467664 }, "communicator.exchange": { "total": 3508.5953525422265, "count": 376158, "is_parallel": true, "self": 3508.5953525422265 }, "steps_from_proto": { "total": 886.8551669376368, "count": 752316, "is_parallel": true, "self": 157.72267335778747, "children": { "_process_rank_one_or_two_observation": { "total": 729.1324935798493, "count": 3009264, "is_parallel": true, "self": 729.1324935798493 } } } } }, "steps_from_proto": { "total": 0.06301791600344586, "count": 56, "is_parallel": true, "self": 0.011793493995810422, "children": { "_process_rank_one_or_two_observation": { "total": 0.05122442200763544, "count": 224, "is_parallel": true, "self": 0.05122442200763544 } } } } } } } } }, "trainer_advance": { "total": 7997.651686768947, "count": 376159, "self": 66.63243717227851, "children": { "process_trajectory": { "total": 989.4638971836682, "count": 376159, "self": 987.3272013546682, "children": { "RLTrainer._checkpoint": { "total": 2.1366958290000184, "count": 11, "self": 2.1366958290000184 } } }, "_update_policy": { "total": 6941.555352413, "count": 268, "self": 687.9706895610225, "children": { "TorchPOCAOptimizer.update": { "total": 6253.584662851978, "count": 8036, "self": 6253.584662851978 } } } } } } }, "trainer_threads": { "total": 1.2359996617306024e-06, "count": 1, "self": 1.2359996617306024e-06 }, "TrainerController._save_models": { "total": 0.2014849029983452, "count": 1, "self": 0.002181223000661703, "children": { "RLTrainer._checkpoint": { "total": 0.1993036799976835, "count": 1, "self": 0.1993036799976835 } } } } } } }