University of Cambridge > Talks.cam > Inference Group > Monte Carlo experiments in computer Go

Monte Carlo experiments in computer Go

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

If you have a question about this talk, please contact Phil Cowans.

Monte Carlo in application to domain of game of Go is a surprisingly strong and promising technique. However experiments show that it’s performance is very sharply limited. At first, after presenting state of the art in this area, I will try to explain both strengths and weaknesses of this approach. Then I will propose an extension of Monte Carlo allowing to overcome it’s limitations. In the end I will present few other modifications and ideas which may allow to further improve this algorithm.

This talk is part of the Inference Group 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