Login / Signup
Learning multi-goal dialogue strategies using reinforcement learning with reduced state-action spaces.
Heriberto Cuayáhuitl
Steve Renals
Oliver Lemon
Hiroshi Shimodaira
Published in:
INTERSPEECH (2006)
Keyphrases
</>
reinforcement learning
action space
state space
state action
continuous state
learning algorithm
control policies
supervised learning
markov decision processes
continuous state spaces
action selection
function approximation
evaluation function
decision theoretic
hidden state
learning tasks
dynamic programming