Reinforcement online learning to rank with unbiased reward shaping.
Shengyao ZhuangZhihao QiaoGuido ZucconPublished in: Inf. Retr. J. (2022)
Keyphrases
- learning to rank
- reward shaping
- balancing exploration and exploitation
- reinforcement learning
- ranking functions
- information retrieval
- loss function
- ranking svm
- document retrieval
- complex domains
- learning to rank algorithms
- collaborative filtering
- evaluation measures
- direct optimization
- reinforcement learning algorithms
- machine learning
- online advertising
- retrieval systems
- text classification
- model free
- learning algorithm
- ranking models
- directly optimize
- test collection
- information retrieval systems
- dynamic programming