UEC student won a exhibition game against CrazyStone without handicap.
Hiroshi Yamashita
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
On 3/15/15 12:39 AM, Hiroshi Yamashita wrote:
UEC student won a exhibition game against CrazyStone without handicap.
Hiroshi Yamashita
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
I was thinking about bootstrapping possibilities, and wondered whether
it would be possible to use a shallower mimic net for positional
evaluation playouts from a specific depth on after having generated
positions with a certain branching factor that typically allows the
actual pro move to be
Hi Hiroshi,
thank you for keeping us informed!
In particular nice to see that there is fresh
computer go blood in Taiwan.
Ingo.
Gesendet: Sonntag, 15. März 2015 um 08:39 Uhr
Von: Hiroshi Yamashita y...@bd.mbn.or.jp
An: computer-go@computer-go.org
Betreff: Re: [Computer-go] UEC Cup
UEC
Hello,
could anyone point me to a current good public source algorithm
for generating valid moves from a given Go board position?
All else failing, i am going to analyze Gnugo first (board.c mostly)
but wanted to ask for hints here first. I am mostly interested in
readability of the algorithm,
Computer Games Workshop at IJCAI 2015
Description
--
A workshop on computer games is to be held at IJCAI 2015 in Buenos Aires,
Argentina. The proceedings will be published with Springer in their
Communications in Computer and
Hi!
On Sun, Mar 15, 2015 at 03:18:46PM +, holger krekel wrote:
could anyone point me to a current good public source algorithm
for generating valid moves from a given Go board position?
All else failing, i am going to analyze Gnugo first (board.c mostly)
but wanted to ask for hints
Hi Petr,
On Sun, Mar 15, 2015 at 19:08 +0100, Petr Baudis wrote:
Hi!
On Sun, Mar 15, 2015 at 03:18:46PM +, holger krekel wrote:
could anyone point me to a current good public source algorithm
for generating valid moves from a given Go board position?
All else failing, i am
You can keep track of pseudo-liberties, where you count a liberty
multiple times if it is adjacent to multiple stones in a chain. That seems
to be the easiest way to implement it, although a serious program will
eventually need the actual liberty count, so perhaps you should just do
that from the