Generative Adversarial User Model for Reinforcement Learning Based Recommendation System

TL;DR

This paper introduces a generative adversarial user model for reinforcement learning in recommendation systems, enabling more accurate user behavior simulation and improved long-term recommendation policies.

Contribution

It proposes a novel model-based RL framework using GANs to imitate user dynamics and a Cascading DQN algorithm for efficient large-scale recommendations.

Findings

GAN-based user model better explains user behavior

RL policy achieves higher long-term rewards

System attains higher click rates in experiments

Abstract

There are great interests as well as many challenges in applying reinforcement learning (RL) to recommendation systems. In this setting, an online user is the environment; neither the reward function nor the environment dynamics are clearly defined, making the application of RL challenging. In this paper, we propose a novel model-based reinforcement learning framework for recommendation systems, where we develop a generative adversarial network to imitate user behavior dynamics and learn her reward function. Using this user model as the simulation environment, we develop a novel Cascading DQN algorithm to obtain a combinatorial recommendation policy which can handle a large number of candidate items efficiently. In our experiments with real data, we show this generative adversarial user model can better explain user behavior than alternatives, and the RL policy based on this model can lead to a better long-term reward for the user and higher click rate for the system.