“Reinforcement
learning: Improving behavior through evaluative feedback”
The field of
reinforcement learning is experiencing a bit of a renaissance. In this talk, I
will survey some of the background and foundations of this subarea and its
relation to other forms of machine learning. I will also describe some of the
recent high-profile successes of reinforcement-learning techniques including
smart thermostats, automatic content filtering, and mastery of games via self
play ranging from 80s-era video games to the ancient board game Go. Time
permitting, I will also plug some of my own research in the area.
Speaker:
Michael L. Littman's
research in machine learning examines algorithms for decision making under
uncertainty. He has earned multiple
awards for teaching and his research has been recognized with three best-paper
awards and two influential paper awards.
Littman has served on the editorial boards for the Journal of Machine
Learning Research and the Journal of Artificial Intelligence Research. He was general chair of International
Conference on Machine Learning 2013 and program chair of the Association for
the Advancement of Artificial Intelligence (AAAI) Conference 2013. He is also a
AAAI Fellow.
- Tags
-