Hi everyone,
Sylvain and myself have had a paper accepted for the Nectar track at
the 23rd Conference on Artificial Intelligence (AAAI-08). The idea of
this track is to summarise previously published results from a
specific field to a wider audience interested in general AI.
Please bear in mind the following:
1. There is no new material in this paper that we have not already
published.
2. There is a 4 page limit, and so there are many details that have
been skipped over in this paper.
3. The learned heuristic, using local shape features, is not used in
the competitive version of MoGo (including the MPI MoGo that played a
professional player last week).
Several people on the mailing list expressed disappointment last year
that they found our ICML paper inaccessible. This paper is intended to
be read by a wider audience, and should hopefully be more accessible.
Having said that, this is still an academic paper for a technical AI
conference, and so some background knowledge is assumed :-)
Here is a draft of the paper, any feedback would be very welcome :-)
http://www.cs.ualberta.ca/~silver/research/publications/files/MoGoNectar.pdf
David and Sylvain
_______________________________________________
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/