ResearchTasksMulti-agent reinforcement learning on Unseen TasksMulti-agent reinforcement learning on Unseen TasksFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedSMAC Stalker-Zealot Medium qualityODIS70.61s3z Performance12Mar 13, 2026