P.G. Sessa

Latest

• Group Robust Preference Optimization in Reward-free RLHF
• Distributionally Robust Model-based Reinforcement Learning with Large State Spaces
• Online Submodular Resource Allocation with Applications to Rebalancing Shared Mobility Systems
• Mixed Strategies for Robust Optimization of Unknown Objectives
• No-Regret Learning in Unknown Games with Correlated Payoffs