Paper ID: 2402.07314

Online Iterative Reinforcement Learning from Human Feedback with General Preference Model

Chenlu Ye, Wei Xiong, Yuheng Zhang, Nan Jiang, Tong Zhang

We study Reinforcement Learning from Human Feedback (RLHF) under a general preference oracle. In particular, we do not assume that there exists a reward function and the preference signal is drawn from the Bradley-Terry model as most of the prior works do. We consider a standard mathematical formulation, the reverse-KL regularized minimax game between two LLMs for RLHF under general preference oracle. The learning objective of this formulation is to find a policy so that it is consistently preferred by the KL-regularized preference oracle over any competing LLMs. We show that this framework is strictly more general than the reward-based one, and propose sample-efficient algorithms for both the offline learning from a pre-collected preference dataset and online learning where we can query the preference oracle along the way of training. Empirical studies verify the effectiveness of the proposed framework.

Submitted: Feb 11, 2024