Efficient Preference Alignment via Pareto Exploration (Student Abstract)

Abstract Hand-craft reward engineering requires domain knowledge with numerous trials and errors, while Preference-based Reinforcement Learning (PbRL) avoids manual reward design but often suffers from limited interpretability and unstable training. To address these issues, we propose a novel preference alignment framework. Our approach leverages large language models to generate sub-reward functions informed by prior knowledge and further align human preferences by optimizing the weights combining these sub-rewards. For policy learning, we introduce Policy Optimization via Pareto Regularization (POPR) which regularizes updates along Pareto-optimal directions. Experiments show that our framework improves reward quality and policy stability, achieving superior performance to expert-designed rewards across most tasks.