<?xml version="1.0" standalone="yes"?>
<Paper uid="N01-1028">
  <Title>Learning optimal dialogue management rules by using reinforcement learning and inductive logic programming</Title>
  <Section position="8" start_page="0" end_page="0" type="concl">
    <SectionTitle>
6 Conclusion
</SectionTitle>
    <Paragraph position="0"> In this paper, we presented an approach for nding and expressing optimal dialogue strategies. We suggested using inductive logic programming to generalize the results given by reinforcement learning methods. The resulting rules are more explicit than the decision tables given by reinforcement learning alone. This allows dialogue designers to better understand the e ect of the optimal strategy and improves potential re-use of the strategies learned. We also show that in some situations rules may have a bene cial e ect when used during learning. By guiding the search based on the best strategy found so far, they can direct a reinforcement learning program towards the optimal strategy, thus reducing the amount of training dialogues needed. More work needs to be done to determine, if possible, under which conditions such improvements can be obtained.</Paragraph>
  </Section>
class="xml-element"></Paper>