Deep Reinforcement Learning for Recommender Systems

Papers

Recommender Systems:

​ SIGIR 20 Neural Interactive Collaborative Filtering paper code

​ KDD 20 Jointly Learning to Recommend and Advertise paper

​ CIKM 20 Whole-Chain Recommendations paper

​ KDD 19 Reinforcement Learning to Optimize Long-term User Engagement in Recommender Systems paper ⭐[JD]

​ DSFAA 19 Reinforcement Learning to Diversify Top-N Recommendation paper code ⭐[JD]

​ KDD 18 Recommendations with Negative Feedback via Pairwise Deep Reinforcement Learning paper ⭐[JD]

​ RecSys 18 Deep Reinforcement Learning for Page-wise Recommendations paper ⭐[JD]

​ DRL4KDD Deep Reinforcement Learning for List-wise Recommendations paper ⭐[JD]

​ Sigweb 19 Deep Reinforcement Learning for Search, Recommendation, and Online Advertising: A Survey paper ⭐[JD]

​ Arxiv 19 Model-Based Reinforcement Learning for Whole-Chain Recommendations paper ⭐[JD]

​ Arxiv 19 Simulating User Feedback for Reinforcement Learning Based Recommendations paper ⭐[JD]

​ Arxiv 19 Deep Reinforcement Learning for Online Advertising in Recommender Systems paper

Search Engine:

​ KDD 18 Reinforcement Learning to Rank in E-Commerce Search Engine Formalization, Analysis, and Application paper ⭐[Alibaba]

Advertisement

​ Arxiv 19 Deep Reinforcement Learning for Online Advertising in Recommender Systems paper

Re-ranking (Top K):

​ IJCAI 19 Reinforcement Learning for Slate-based Recommender Systems: A Tractable Decomposition and Practical Methodology paper arxiv ⭐[Google]

​ Arixv 19 Seq2Slate: Re-ranking and Slate Optimization with RNNs paper ⭐[Google]

​ KDD 19 Exact-K Recommendation via Maximal Clique Optimization paper ⭐[Alibaba]

​ WWW 19 Value-aware Recommendation based on Reinforcement Profit Maximization paper code Dataset ⭐[Alibaba]

Bandit:

​ WWW 10 A Contextual-Bandit Approach to Personalized News Article Recommendation paper

​ KDD 16 Online Context-Aware Recommendation with Time Varying Multi-Armed Bandit paper

​ CIKM 17 Returning is Believing Optimizing Long-term User Engagement in Recommender Systems

​ ICLR 18 Deep Learning with Logged Bandit Feedback paper

​ Recsys 18 Explore, Exploit, and Explain Personalizing Explainable Recommendations with Bandits paper

Hierarchical RL

​ AAAI19 Hierarchical Reinforcement Learning for Course Recommendation in MOOCs paper

​ WWW 19 Aggregating E-commerce Search Results from Heterogeneous Sources via Hierarchical Reinforcement Learning paper ⭐[Alibaba]

DQN:

​ WWW 18 DRN: A Deep Reinforcement Learning Framework for News Recommendation paper ⭐[Microsoft]

​ KDD 18 Stabilizing Reinforcement Learning in Dynamic Environment with Application to Online Recommendation paper ⭐[Alibaba]

​ ICML 19 Off-Policy Deep Reinforcement Learning without Exploration paper

Policy Gradient:

​ WSDM 19 Top-K Off-Policy Correction for a REINFORCE Recommender System paper ⭐[Google]

​ NIPS 17 Off-policy evaluation for slate recommendation paper

​ ICML 19 Safe Policy Improvement with Baseline Bootstrapping paper

​ WWW 19 Policy Gradients for Contextual Recommendations paper

​ AAAI 19 Large-scale Interactive Recommendation with Tree-structured Policy Gradient paper

Actor-Critic:

​ Arxiv 15 Deep Reinforcement Learning in Large Discrete Action Spaces paper code

​ Arxiv 18 Deep Reinforcement Learning based Recommendation with Explicit User-Item Interactions Modeling paper

​ KDD 18 Supervised Reinforcement Learning with Recurrent Neural Network for Dynamic Treatment Recommendation paper

Multi-agent:

​ WWW 18 Learning to Collaborate Multi-Scenario Ranking via Multi-Agent Reinforcement Learning paper

⭐[Alibaba]

Offline:

​ WSDM 19 Offline Evaluation to Make Decisions About Playlist Recommendation Algorithms paper

​ KDD 19 Off-policy Learning for Multiple Loggers paper

Explainable:

​ ICDM 18 A Reinforcement Learning Framework for Explainable Recommendation paper

​ SIGIR 19 Reinforcement Knowledge Graph Reasoning for Explainable Recommendation paper

Simulation:

​ ICML 19 Generative Adversarial User Model for Reinforcement Learning Based Recommendation System paper

Research Scientists:

Jun Wang, Jun Xu, Weinan Zhang, Xiangyu Zhao, Lixin Zou