Alleviating Matthew Effect of Offline Reinforcement Learning in Interactive Recommendation.
Chongming GaoKexin HuangJiawei ChenYuan ZhangBiao LiPeng JiangShiqi WangZhong ZhangXiangnan HePublished in: SIGIR (2023)
Keyphrases
- reinforcement learning
- collaborative filtering
- function approximation
- recommender systems
- real time
- optimal policy
- machine learning
- reinforcement learning algorithms
- model free
- markov decision processes
- virtual reality
- computer graphics
- user interaction
- multi agent
- recommendation systems
- temporal difference
- learning algorithm
- autonomous learning
- user preferences
- dynamic programming
- computer vision
- graphical interface
- contextual bandit