Deep Reinforcement Learning for List-wise Recommendations

TL;DR

This paper introduces a reinforcement learning-based recommender system that dynamically improves its strategies through user interactions, utilizing list-wise recommendations and an online simulation environment to enhance personalization.

Contribution

It presents a novel RL framework for list-wise recommendations that adaptively learns from user feedback and incorporates list-wide strategies, validated on real-world e-commerce data.

Findings

Reinforcement learning effectively improves recommendation strategies.

List-wise recommendations outperform point-wise approaches.

The online environment simulator enhances offline training and evaluation.

Abstract

Recommender systems play a crucial role in mitigating the problem of information overload by suggesting users' personalized items or services. The vast majority of traditional recommender systems consider the recommendation procedure as a static process and make recommendations following a fixed strategy. In this paper, we propose a novel recommender system with the capability of continuously improving its strategies during the interactions with users. We model the sequential interactions between users and a recommender system as a Markov Decision Process (MDP) and leverage Reinforcement Learning (RL) to automatically learn the optimal strategies via recommending trial-and-error items and receiving reinforcements of these items from users' feedbacks. In particular, we introduce an online user-agent interacting environment simulator, which can pre-train and evaluate model parameters offline before applying the model online. Moreover, we validate the importance of list-wise recommendations during the interactions between users and agent, and develop a novel approach to incorporate them into the proposed framework LIRD for list-wide recommendations. The experimental results based on a real-world e-commerce dataset demonstrate the effectiveness of the proposed framework.