Amy Zhang

4 papers University of Texas at Austin

• ExPO: Unlocking Hard Reasoning with Self-Explanation-Guided Reinforcement Learning
• Information-Theoretic Reward Decomposition for Generalizable RLHF
• RLZero: Direct Policy Inference from Language Without In-Domain Supervision
• Uni-RL: Unifying Online and Offline RL via Implicit Value Regularization