Supervised Advantage Actor-Critic for Recommender Systems.
Xin XinAlexandros KaratzoglouIoannis ArapakisJoemon M. JosePublished in: WSDM (2022)
Keyphrases
- recommender systems
- actor critic
- reinforcement learning
- collaborative filtering
- policy gradient
- gradient method
- approximate dynamic programming
- matrix factorization
- optimal control
- function approximation
- semi supervised
- learning algorithm
- supervised learning
- temporal difference
- convergence rate
- neuro fuzzy
- linear program
- reinforcement learning algorithms
- policy iteration
- multi agent
- machine learning
- average reward
- fuzzy logic