KERL

Pengfei Wang, Fan Yu, Long Xia, Wayne Xin Zhao, Shaozhang Niu, Jimmy Xiangji Huang

2020 · 121 citations · 22 references

Concepts

Abstract

For sequential recommendation, it is essential to capture and predict future or long-term user preference for generating accurate recommendation over time. To improve the predictive capacity, we adopt reinforcement learning (RL) for developing effective sequential recommenders. However, user-item interaction data is likely to be sparse, complicated and time-varying. It is not easy to directly apply RL techniques to improve the performance of sequential recommendation.

References

22