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
Type
Preprint
Publication
arXiv:2503.15477, 2025
Language Models Reward Models Reinforcement Learning Reinforcement Learning from Human Feedback Policy Gradient Alignment

Related