ResearchDatasetsSMAXSMAXFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultssmacv2_10_unitsSMAX SMACv275Average Win Rate7smacv2_5_unitsSMAX SMAC v281Average Win Rate7Cooperative Multi-Agent Reinforcement LearningSMAX0.92IQM of Normalized Returns3Goal-conditioned Reinforcement LearningSMAX95.6IQM2