RLHF

Event Weekly OptiML Lab Group Meeting Short summary In this seminar, I will talk about my own paper “Improved Regret Bounds of (Multinomial) Logistic Bandits via Regret-to-Confidence-Set Conversion” (Lee et al.

Event Weekly OptiML Lab Group Meeting Short summary In this talk, I will first (somewhat rigorously) introduce the framework of reinforcement learning with human feedback (RLHF). Then I will go over three recent breakthroughs in the analysis and improvement of RLHF.

We consider the problem of contextual online RLHF with general preferences, where the goal is to identify the Nash Equilibrium. We …