Sign in
Switch-Based Active Deep Dyna-Q: Efficient Adaptive Planning for Task-Completion Dialogue Policy Learning.
Yuexin Wu
Xiujun Li
Jingjing Liu
Jianfeng Gao
Yiming Yang
Published in:
AAAI (2019)
Keyphrases
</>
learning algorithm
supervised learning
learning process
adaptive learning
knowledge acquisition
action selection
reinforcement learning
domain independent
macro actions
unsupervised learning
learning systems
learning tasks
mixed initiative
human computer
predictive state representations