[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: computer-go: Neural networks



On Wed, 16 May 2001, Richard Brown wrote:

> Nicol Schraudolph, Peter Dayan, and Terrence J. Sejnowski of the
> Computational Neurobiology Lab at the Salk Institute wrote a paper
> about neural networks which learn to evaluate 9x9 go positions using
> temporal differences:
>   <http://satirist.org/learn-game/systems/go-net.html>

For the record, an expanded version of that paper has recently been
published in a Springer book:

@inbook{nngochap,
     author = {Nicol N. Schraudolph and Peter Dayan
               and Terrence J. Sejnowski},
      title = {Learning to Evaluate Go Positions
               via Temporal Difference Methods},
    chapter =  4,
      pages = {77--98},
     editor = {Norio Baba and Lakhmi C. Jain},
  booktitle = {Computational Intelligence in Games},
  publisher = {Springer Verlag, Berlin},
     series = {Studies in Fuzziness and Soft Computing},
     volume =  62,
       year =  2001
}

You can find it online at:   ftp://ftp.idsia.ch/pub/nic/gochap.ps.gz

No new work - just more details and a bit of updating.  The original paper
is from 1993 and showing its age.  I hope to get a new and improved effort
going in the near future...

Best wishes,

- Nici.

-- 
    Dr. Nicol N. Schraudolph                http://www.idsia.ch/~nic/
    Institute of Computational Sciences     mobile:   +41-76-585-3877
    ETH Zentrum, WET D, Weinbergstr. 43     office:       -1-632-7942
    CH-8092 Zuerich, Switzerland               fax:             -1703