Best-of-Both-Worlds Multi-Dueling Bandits: Unified Algorithms for Stochastic and Adversarial Preferences under Condorcet and Borda Objectives

S Akash, Pratik Gajane, Jawar Singh

Multi-dueling bandits, where a learner selects $m\ge 2$ arms per round and observes only the winner, arise naturally in many applications including ranking and recommendation sys…