Login / Signup
Gaussian Process based Deep Dyna-Q approach for Dialogue Policy Learning.
Guanlin Wu
Wenqi Fang
Ji Wang
Jiang Cao
Weidong Bao
Yang Ping
Xiaomin Zhu
Zheng Wang
Published in:
ACL/IJCNLP (Findings) (2021)
Keyphrases
</>
gaussian process
learning process
gaussian processes
model selection
prior knowledge
learning tasks
learning problems
similarity measure
lower bound
probability distribution
semi supervised
supervised learning
co occurrence
higher order