University of Cambridge > Talks.cam > CUED Speech Group Seminars > Inverse reinforcement learning for modeling micro-turn taking

Inverse reinforcement learning for modeling micro-turn taking

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Rogier van Dalen.

Inverse reinforcement learning (IRL) is a technique for recovering a decision-making agent’s underlying reward function by observing its behaviour in interaction with a specific environmental model. The significance of IRL stems from its ability to solve problems in a diverse range of research areas where an agent’s behavior can be characterised by a reward function which reflects the agent’s objective and preferences. In this talk, we present an application of IRL to micro-turn interaction analysis, aiming at identifying the conversational agent’s objective in the turn-taking behavior and developing a micro-turn manager for incremental dialogue systems.

This talk is part of the CUED Speech Group Seminars series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2019 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity