ACP based reinforcement learning for long-term recommender system.
Tianyi HuangMin LiWilliam ZhuPublished in: Int. J. Mach. Learn. Cybern. (2022)
Keyphrases
- long term
- recommender systems
- reinforcement learning
- short term
- collaborative filtering
- function approximation
- model free
- information filtering
- reinforcement learning algorithms
- user preferences
- optimal policy
- learning process
- state space
- markov decision processes
- optimal control
- movie recommendation
- temporal difference
- user profiles
- user model
- transfer learning
- implicit feedback
- cold start problem
- product recommendation
- robotic control
- information overload
- matrix factorization
- data sets
- dynamic programming
- multi agent
- website
- metadata
- learning algorithm