Deep reinforcement learning for search, recommendation, and online advertising: a survey

TL;DR

This survey reviews how deep reinforcement learning enhances search, recommendation, and online advertising by enabling real-time strategy updates and optimizing long-term user engagement.

Contribution

It provides a comprehensive overview of DRL methodologies, algorithms, and applications in information seeking, highlighting recent advances and future research directions.

Findings

DRL enables real-time adaptation of search and recommendation strategies.

DRL techniques improve long-term user engagement and satisfaction.

The survey identifies promising research directions in DRL for information retrieval.

Abstract

Search, recommendation, and online advertising are the three most important information-providing mechanisms on the web. These information seeking techniques, satisfying users' information needs by suggesting users personalized objects (information or services) at the appropriate time and place, play a crucial role in mitigating the information overload problem. With recent great advances in deep reinforcement learning (DRL), there have been increasing interests in developing DRL based information seeking techniques. These DRL based techniques have two key advantages -- (1) they are able to continuously update information seeking strategies according to users' real-time feedback, and (2) they can maximize the expected cumulative long-term reward from users where reward has different definitions according to information seeking applications such as click-through rate, revenue, user satisfaction and engagement. In this paper, we give an overview of deep reinforcement learning for search, recommendation, and online advertising from methodologies to applications, review representative algorithms, and discuss some appealing research directions.