ROLeR: Effective Reward Shaping in Offline Reinforcement Learning for Recommender Systems

TL;DR

ROLeR introduces a novel reward shaping method and improved uncertainty estimation for offline reinforcement learning in recommender systems, leading to state-of-the-art performance on benchmark datasets.

Contribution

The paper proposes ROLeR, a new approach that enhances reward modeling and uncertainty estimation in model-based offline RL for recommender systems.

Findings

ROLeR outperforms existing baselines on four benchmark datasets.

The non-parametric reward shaping improves reward model accuracy.

Enhanced uncertainty penalties lead to better recommendation performance.

Abstract

Offline reinforcement learning (RL) is an effective tool for real-world recommender systems with its capacity to model the dynamic interest of users and its interactive nature. Most existing offline RL recommender systems focus on model-based RL through learning a world model from offline data and building the recommendation policy by interacting with this model. Although these methods have made progress in the recommendation performance, the effectiveness of model-based offline RL methods is often constrained by the accuracy of the estimation of the reward model and the model uncertainties, primarily due to the extreme discrepancy between offline logged data and real-world data in user interactions with online platforms. To fill this gap, a more accurate reward model and uncertainty estimation are needed for the model-based RL methods. In this paper, a novel model-based Reward Shaping in Offline Reinforcement Learning for Recommender Systems, ROLeR, is proposed for reward and uncertainty estimation in recommendation systems. Specifically, a non-parametric reward shaping method is designed to refine the reward model. In addition, a flexible and more representative uncertainty penalty is designed to fit the needs of recommendation systems. Extensive experiments conducted on four benchmark datasets showcase that ROLeR achieves state-of-the-art performance compared with existing baselines. The source code can be downloaded at https://github.com/ArronDZhang/ROLeR.