Dynamic Multi-Objective Recommendation Via Discrete Soft Actor-Critic

https://doi.org/10.55640/irjlis-v02i05-01
Section: Articles Published Date: 2025-05-01 Pages: 1-5 Views: 0 Downloads: 2

Authors

  • Dr. Wei Jun Liu Department of Computer Science, School of Information Technology, Tsinghua University, Beijing, China
  • Yiming Chen Centre for Intelligent Artificial Networks (CIAN), Department of Artificial Intelligence, Zhejiang University, Hangzhou, China
PDF

Abstract

Modern recommender systems often need to optimize multiple conflicting objectives, such as accuracy, diversity, and novelty. This paper proposes a novel approach, Dynamic Multi-Objective Recommendation via Discrete Soft Actor-Critic (DMOR-DSAC), to address this challenge. DMOR-DSAC employs a reinforcement learning framework with a discrete action space, utilizing the Soft Actor-Critic algorithm to learn a policy that dynamically balances these objectives. Experimental results on benchmark datasets demonstrate the effectiveness of DMOR-DSAC in achieving superior multi-objective performance compared to existing methods.

Keywords

Multi-objective recommendation, reinforcement learning, Soft Actor-Critic

Most read articles by the same author(s)