A General Offline Reinforcement Learning Framework for Interactive Recommendation

Author:

Xiao Teng,Wang Donglin

Abstract

This paper studies the problem of learning interactive recommender systems from logged feedbacks without any exploration in online environments. We address the problem by proposing a general offline reinforcement learning framework for recommendation, which enables maximizing cumulative user rewards without online exploration. Specifically, we first introduce a probabilistic generative model for interactive recommendation, and then propose an effective inference algorithm for discrete and stochastic policy learning based on logged feedbacks. In order to perform offline learning more effectively, we propose five approaches to minimize the distribution mismatch between the logging policy and recommendation policy: support constraints, supervised regularization, policy constraints, dual constraints and reward extrapolation. We conduct extensive experiments on two public real-world datasets, demonstrating that the proposed methods can achieve superior performance over existing supervised learning and reinforcement learning methods for recommendation.

Publisher

Association for the Advancement of Artificial Intelligence (AAAI)

Subject

General Medicine

Cited by 30 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. On the Opportunities and Challenges of Offline Reinforcement Learning for Recommender Systems;ACM Transactions on Information Systems;2024-08-19

2. M 3 Rec: A Context-Aware Offline Meta-Level Model-Based Reinforcement Learning Approach for Cold-Start Recommendation;ACM Transactions on Information Systems;2024-08-19

3. Disentangling User Cognitive Intent with Causal Reasoning for Knowledge-Enhanced Recommendation;Cognitive Computation;2024-07-18

4. Rethinking Offline Reinforcement Learning for Sequential Recommendation from A Pair-Wise Q-Learning Perspective;2024 International Joint Conference on Neural Networks (IJCNN);2024-06-30

5. A Counterfactual Neural Causal Model for Interactive Recommendation;2024 27th International Conference on Computer Supported Cooperative Work in Design (CSCWD);2024-05-08

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3