A recursive dialogue game framework with optimal Policy offering personalized computer-assisted language learning.
Pei-hao SuYow-Bang WangTsung-Hsien WenTien-han YuLin-Shan LeePublished in: INTERSPEECH (2013)
Keyphrases
- optimal policy
- computer assisted language learning
- dynamic programming
- decision problems
- long run
- state space
- infinite horizon
- finite horizon
- natural language
- markov decision processes
- language learning
- markov decision process
- state dependent
- reinforcement learning
- bayesian reinforcement learning
- college students
- computer technology