Login / Signup
Learning to control listening-oriented dialogue using partially observable markov decision processes.
Toyomi Meguro
Yasuhiro Minami
Ryuichiro Higashinaka
Kohji Dohsaka
Published in:
ACM Trans. Speech Lang. Process. (2013)
Keyphrases
</>
learning algorithm
reinforcement learning
partially observable markov decision processes
continuous state
stochastic domains
finite state
partially observable
predictive state representations
partially observable domains