Deep reinforcement learning for recommender systems

Isshu Munemasa, Yuta Tomomatsu, Kunioki Hayashi, Tomohiro Takagi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

Services that introduce stores to users on the Internet are increasing in recent years. Each service conducts thorough analyses in order to display stores matching each user's preferences. In the field of recommendation, collaborative filtering performs well when there is sufficient click information from users. Generally, when building a user-item matrix, data sparseness becomes a problem. It is especially difficult to handle new users. When sufficient data cannot be obtained, a multi-armed bandit algorithm is applied. Bandit algorithms advance learning by testing each of a variety of options sufficiently and obtaining rewards (i.e. feedback). It is practically impossible to learn everything when the number of items to be learned periodically increases. The problem of having to collect sufficient data for a new user of a service is the same as the problem that collaborative filtering faces. In order to solve this problem, we propose a recommender system based on deep reinforcement learning. In deep reinforcement learning, a multilayer neural network is used to update the value function.

Original languageEnglish
Title of host publication2018 International Conference on Information and Communications Technology, ICOIACT 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages226-233
Number of pages8
ISBN (Electronic)9781538609545
DOIs
Publication statusPublished - 26 Apr 2018
Event1st International Conference on Information and Communications Technology, ICOIACT 2018 - Yogyakarta, Indonesia
Duration: 6 Mar 20187 Mar 2018

Publication series

Name2018 International Conference on Information and Communications Technology, ICOIACT 2018
Volume2018-January

Conference

Conference1st International Conference on Information and Communications Technology, ICOIACT 2018
CountryIndonesia
CityYogyakarta
Period6/03/187/03/18

Keywords

  • Deep Deterministic Policy Gradient
  • Deep Reinforcement Learning
  • Latent Dirichlet Allocation
  • Recommender systems

Fingerprint Dive into the research topics of 'Deep reinforcement learning for recommender systems'. Together they form a unique fingerprint.

  • Cite this

    Munemasa, I., Tomomatsu, Y., Hayashi, K., & Takagi, T. (2018). Deep reinforcement learning for recommender systems. In 2018 International Conference on Information and Communications Technology, ICOIACT 2018 (pp. 226-233). (2018 International Conference on Information and Communications Technology, ICOIACT 2018; Vol. 2018-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICOIACT.2018.8350761