Deep Reinforcement Learning based Group Recommender System

Zefang Liu, Shuran Wen, Yinzhu Quan

arXiv preprint arXiv:2106.06900, 2021

Abstract

Group recommender systems are widely used in current web applications. In this paper, we propose a novel group recommender system based on the deep reinforcement learning. We introduce the MovieLens data at first and generate one random group dataset, MovieLens-Rand, from it. This randomly generated dataset is described and analyzed. We also present experimental settings and two state-of-art baselines, AGREE and GroupIM. The framework of our novel model, the Deep Reinforcement learning based Group Recommender system (DRGR), is proposed. Actor-critic networks are implemented with the deep deterministic policy gradient algorithm. The DRGR model is applied on the MovieLens-Rand dataset with two baselines. Compared with baselines, we conclude that DRGR performs better than GroupIM due to long interaction histories but worse than AGREE because of the self-attention mechanism. We express advantages and shortcomings of DRGR and also give future improvement directions at the end.

Recommended citation: Liu, Zefang, Shuran Wen, and Yinzhu Quan. "Deep Reinforcement Learning based Group Recommender System." arXiv preprint arXiv:2106.06900 (2021).
[Download Paper] [Download Slides] [Download Code]