What Makes a Reward Model a Good Teacher? An Optimization Perspective

Noam Razin, Zixuan Wang, Hubert Strauss, Stanley Wei, Jason D. Lee, Sanjeev Arora
March 2025
PDF Code Poster
Type
Conference paper
Publication
Advances in Neural Information Processing Systems (NeurIPS), 2025
Language Models Reward Models Reinforcement Learning Reinforcement Learning from Human Feedback Policy Gradient Alignment

Related