Sign in
User Satisfaction Reward Estimation Across Domains: Domain-independent Dialogue Policy Learning.
Stefan Ultes
Wolfgang Maier
Published in:
Dialogue Discourse (2021)
Keyphrases
</>
domain independent
user satisfaction
domain specific
domain dependent
control knowledge
hand coded
reinforcement learning
domain specific knowledge
knowledge acquisition
macro operators
learning process
background knowledge
inductive learning
explanation based learning
inverse reinforcement learning