{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.1676442623138428, "min": 3.1411008834838867, "max": 3.2957351207733154, "count": 232 }, "SoccerTwos.Policy.Entropy.sum": { "value": 70448.40625, "min": 22155.142578125, "max": 156177.34375, "count": 232 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 903.0, "min": 416.45454545454544, "max": 999.0, "count": 232 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 21672.0, "min": 12460.0, "max": 27804.0, "count": 232 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1198.5690931650881, "min": 1193.063294954257, "max": 1207.1904214672236, "count": 138 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2397.1381863301763, "min": 2386.126589908514, "max": 12030.76499202371, "count": 138 }, "SoccerTwos.Step.mean": { "value": 2319182.0, "min": 9918.0, "max": 2319182.0, "count": 232 }, "SoccerTwos.Step.sum": { "value": 2319182.0, "min": 9918.0, "max": 2319182.0, "count": 232 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0018293745815753937, "min": -0.09339082986116409, "max": 0.012058364227414131, "count": 232 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.02012312039732933, "min": -1.400862455368042, "max": 0.12091680616140366, "count": 232 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0014848989667370915, "min": -0.09344816207885742, "max": 0.011044774204492569, "count": 232 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.016333889216184616, "min": -1.401706337928772, "max": 0.13135787844657898, "count": 232 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 232 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 232 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.10487272522666237, "min": -0.5333333333333333, "max": 0.3658933281898499, "count": 232 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 1.1535999774932861, "min": -8.0, "max": 5.488399922847748, "count": 232 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.10487272522666237, "min": -0.5333333333333333, "max": 0.3658933281898499, "count": 232 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 1.1535999774932861, "min": -8.0, "max": 5.488399922847748, "count": 232 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 232 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 232 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015955663394803803, "min": 0.00886147110334908, "max": 0.02335223377837489, "count": 107 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015955663394803803, "min": 0.00886147110334908, "max": 0.02335223377837489, "count": 107 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0008029293671521979, "min": 1.882866570213082e-07, "max": 0.0036716784505794447, "count": 107 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0008029293671521979, "min": 1.882866570213082e-07, "max": 0.0036716784505794447, "count": 107 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0008045330866783237, "min": 1.8708090081531737e-07, "max": 0.003675629124821474, "count": 107 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0008045330866783237, "min": 1.8708090081531737e-07, "max": 0.003675629124821474, "count": 107 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 107 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 107 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 107 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 107 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 107 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 107 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1725459457", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/poca/SoccerTwos.yaml --env=/content/training-envs-executables/linux/SoccerTwos.x86_64 --run-id=SoccerTwos2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1725464582" }, "total": 5124.486239383001, "count": 1, "self": 0.23174353300055373, "children": { "run_training.setup": { "total": 0.052237429999991036, "count": 1, "self": 0.052237429999991036 }, "TrainerController.start_learning": { "total": 5124.20225842, "count": 1, "self": 3.4192652389720024, "children": { "TrainerController._reset_env": { "total": 3.7538606070012293, "count": 12, "self": 3.7538606070012293 }, "TrainerController.advance": { "total": 5116.468793763028, "count": 151690, "self": 3.635871973166104, "children": { "env_step": { "total": 4238.218074417985, "count": 151690, "self": 3087.1959936429766, "children": { "SubprocessEnvManager._take_step": { "total": 1148.9534307120502, "count": 151690, "self": 24.7778011172677, "children": { "TorchPolicy.evaluate": { "total": 1124.1756295947825, "count": 301330, "self": 1124.1756295947825 } } }, "workers": { "total": 2.068650062957886, "count": 151689, "self": 0.0, "children": { "worker_root": { "total": 5115.227011365101, "count": 151689, "is_parallel": true, "self": 2521.6270250069565, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002925751000020682, "count": 2, "is_parallel": true, "self": 0.0008306990002893144, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020950519997313677, "count": 8, "is_parallel": true, "self": 0.0020950519997313677 } } }, "UnityEnvironment.step": { "total": 0.039634767999928044, "count": 1, "is_parallel": true, "self": 0.0011655649999511297, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0008309490000328879, "count": 1, "is_parallel": true, "self": 0.0008309490000328879 }, "communicator.exchange": { "total": 0.03413032200000998, "count": 1, "is_parallel": true, "self": 0.03413032200000998 }, "steps_from_proto": { "total": 0.003507931999934044, "count": 2, "is_parallel": true, "self": 0.0006255759998339272, "children": { "_process_rank_one_or_two_observation": { "total": 0.002882356000100117, "count": 8, "is_parallel": true, "self": 0.002882356000100117 } } } } } } }, "UnityEnvironment.step": { "total": 2593.5753156231476, "count": 151688, "is_parallel": true, "self": 160.897112554248, "children": { "UnityEnvironment._generate_step_input": { "total": 114.16832647205035, "count": 151688, "is_parallel": true, "self": 114.16832647205035 }, "communicator.exchange": { "total": 1800.066735114799, "count": 151688, "is_parallel": true, "self": 1800.066735114799 }, "steps_from_proto": { "total": 518.4431414820502, "count": 303376, "is_parallel": true, "self": 85.9873074883626, "children": { "_process_rank_one_or_two_observation": { "total": 432.45583399368763, "count": 1213504, "is_parallel": true, "self": 432.45583399368763 } } } } }, "steps_from_proto": { "total": 0.024670734997243926, "count": 22, "is_parallel": true, "self": 0.005079068993381952, "children": { "_process_rank_one_or_two_observation": { "total": 0.019591666003861974, "count": 88, "is_parallel": true, "self": 0.019591666003861974 } } } } } } } } }, "trainer_advance": { "total": 874.6148473718769, "count": 151689, "self": 29.26396912061398, "children": { "process_trajectory": { "total": 244.21010626226007, "count": 151689, "self": 243.33139389226062, "children": { "RLTrainer._checkpoint": { "total": 0.8787123699994481, "count": 4, "self": 0.8787123699994481 } } }, "_update_policy": { "total": 601.1407719890028, "count": 107, "self": 353.26367217101324, "children": { "TorchPOCAOptimizer.update": { "total": 247.87709981798957, "count": 3216, "self": 247.87709981798957 } } } } } } }, "trainer_threads": { "total": 1.4319994079414755e-06, "count": 1, "self": 1.4319994079414755e-06 }, "TrainerController._save_models": { "total": 0.560337378999975, "count": 1, "self": 0.006237005000002682, "children": { "RLTrainer._checkpoint": { "total": 0.5541003739999724, "count": 1, "self": 0.5541003739999724 } } } } } } }