Controlling the Risk of Conversational Search via Reinforcement Learning.
Zhenduo WangQingyao AiPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- search algorithm
- multi modal
- learning algorithm
- state space
- search space
- search strategy
- search strategies
- function approximation
- natural language
- learning process
- dynamic programming
- machine learning
- markov decision processes
- search methods
- keyword search
- search queries
- optimal control
- conversational agent