University of Cambridge > Talks.cam > Churchill CompSci Talks > Pass Go and collect $200: how slot machines are advancing the state of the art in computer go AI

Pass Go and collect $200: how slot machines are advancing the state of the art in computer go AI

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

If you have a question about this talk, please contact Matthew Ireland.

In 2006 a huge revolution in computer go engines occurred when Monte Carlo search was discovered to be many times stronger than the techniques that were traditionally used. In this talk we will explore what makes the game of go so hard for computers, and how the Monte Carlo Tree Search algorithm tackles these difficulties. The theory of multi-armed bandits will come into play when choosing the best move to explore next, with discussion of the asymptotically-optimal UCB1 strategy. Refinements of the basic algorithm will be discussed, including AMAF /RAVE and heavy playouts, taking us to ongoing topics in research.

This talk is part of the Churchill CompSci Talks series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2018 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity