Reinforcement Learning Based on Contextual Bandits for Personalized Online Learning Recommendation Systems.
Wacharawan IntayoadChayapol KamyodPunnarumol TemdeePublished in: Wirel. Pers. Commun. (2020)
Keyphrases
- recommendation systems
- online learning
- reinforcement learning
- user modeling
- e learning
- personalized recommendation
- personalized services
- web personalization
- collaborative filtering
- regret bounds
- collaborative filtering recommendation algorithm
- user preferences
- contextual information
- recommender systems
- web search
- user profiles
- multi armed bandit
- state space
- user feedback
- search engine
- active learning
- recommendation quality
- learning algorithm
- machine learning
- optimal policy
- stochastic systems
- learning process
- social recommendation
- recommendation algorithms
- search queries
- transfer learning
- learning experience
- digital libraries