Preference learning is a key technology for aligning language models with human values. Reinforcement Learning from Human Feedback (RLHF) is a model based algorithm to optimize preference learning, which first fitting a reward model for preference score, and then optimizing generating policy with on-policy PPO algorithm to maximize the reward. The processing of RLHF is complex, time-consuming and unstable. Direct Preference Optimization (DPO) algorithm using off-policy algorithm to direct optimize generating policy and eliminating the need for reward model, which is data efficient and stable. DPO use Bradley-Terry model and log-loss which leads to over-fitting to the preference data at the expense of ignoring KL-regularization term when preference near deterministic. IPO uses a root-finding pairwise MSE loss to solve the ignoring KL-regularization problem, and learning an optimal policy. But IPO's pairwise loss still can't s make the KL-regularization to work. In this paper, we design a simple and intuitive off-policy preferences optimization algorithm from an importance sampling view, and add an off-policy KL-regularization term which makes KL-regularization truly effective. To simplify the learning process and save memory usage, we can generate regularization data in advance, which eliminate the needs for both reward model and reference policy in the stage of optimization.

这篇论文介绍了一种重要的技术——偏好学习，其中Reinforcement Learning from Human Feedback（RLHF）是一种优化偏好学习的模型算法，通过对偏好得分建立奖励模型并优化生成策略；为了提高数据效率和稳定性，提出了使用离策略算法进行直接优化生成策略的Direct Preference Optimization（DPO）算法；通过增加离策略KL正则化项实现了KL正则化的真正有效性。

偏好作为奖励，通过重要性采样进行最大偏好优化