ResearchTasksUncoupled learning with bandit feedbackUncoupled learning with bandit feedbackFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedZero-sum matrix gamesCai et al. 2023 (Algorithm 1)1Convergence Rate Bound6Apr 20, 2026