ResearchTasksSafe Multi-Agent Reinforcement LearningSafe Multi-Agent Reinforcement LearningFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedWireless Communication 25 agentsScalable Primal-Dual Actor-Critic19.26Constraint Violation Rate4Feb 26, 2026Pistonball 10 agentsScalable Primal-Dual Actor-Critic4.919Constraint Violation Rate4Feb 26, 2026
Wireless Communication 25 agentsScalable Primal-Dual Actor-Critic19.26Constraint Violation Rate4Feb 26, 2026