Discriminative Deep Dyna-Q: Robust Planning for Dialogue Policy Learning.

Shang-Yu Su Xiujun Li Jianfeng Gao Jingjing Liu Yun-Nung Chen

Published in: CoRR (2018)

Keyphrases

learning algorithm
action selection
reinforcement learning
learning process
learning systems
machine learning
active learning
discriminative learning
supervised learning
unsupervised learning
learning tasks
learning problems
human computer
structured output