ProRL: Effective Reinforcement Learning for Proactive Recommendation via Rectified Policy Gradient Estimation

摘要

Proactive Recommender Systems (PRSs) aim to guide user preference shift toward target items by generating paths of intermediate recommendations. Reinforcement learning (RL) provides a principled framework for optimizing such sequential decision tasks. Based on path rewards, RL can naturally jointly optimize short-term acceptance and long-term guidance effectiveness. However, naively applying policy gradients to PRS results in deficient gradient estimation. It has been observed that length-dependent bias causes gradients to favor path extension over deeper exploration, while weighting each step by path-level reward leads to high gradient variance. To rectify these two deficiencies, we propose an effective RL framework $\textbf{ProRL}$ with two novel mechanisms for proactive recommendation. First, Stepwise Reward Centering subtracts expected rewards to neutralize length-dependent bias, ensuring that path extension yields zero expected gradient signal. Second, Position-Specific Advantage Estimation leverages the reward decomposition structure to compute step-dependent baselines, reducing gradient variance. Together, these mechanisms yield policy gradients that precisely target path quality. Our experiments on three real-world datasets demonstrate that ProRL significantly outperforms state-of-the-art PRSs. Our codes are available at https://anonymous.4open.science/r/ProRL-D56DHM.