Reinforcement Learning from Human Feedback with Active Queries.
Kaixuan JiJiafan HeQuanquan GuPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- query processing
- query language
- query refinement
- human operators
- function approximation
- complex queries
- database
- response time
- efficient processing
- range queries
- database queries
- feedback information
- temporal difference
- tutorial dialogue
- user engagement
- human subjects
- human users
- query evaluation
- user queries
- state space
- dynamic programming
- neural network
- user feedback
- relevance feedback
- learning algorithm