wow .. congrats to the AlphaGo team!!
On Tue, Mar 8, 2016 at 11:43 PM, Hiroshi Yamashita wrote:
> AlphaGo won 1st game against Lee Sedol!
>
> Hiroshi Yamashita
>
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
>
Can you reproduce it issuing gtp commands, i.e., loading in the failing
position from sgf-file and requesting gnugo to generate a move?
Example:
loadsgf games/strategy25.sgf 61
gg_genmove black
On Thu, Jun 18, 2015 at 3:56 PM, Petr Baudis pa...@ucw.cz wrote:
Hi!
I've observed the
Looking at the lightest playout version of my bitmap-based 9x9 program
(source-code somewhere in the archives), I spent an estimated 2% of the
time generating random numbers, so 40% seems to indicate something is not
right, such as re-initializing the generator all the time.
The execution time of
Correct me if I am wrong, but I believe that the CrazyStone approach of
team-of-features can be cast in terms of a shallow neural network. The
inputs are matched patterns on the board and other local information on
atari, previous moves, ko situation, and such. Remi alluded as much on this
list
Denis,
2009/12/4 Denis fidaali denis.fida...@hotmail.fr
o much complexity could be removed by not maintaining atari status for
strings (especially for capturing moves)
but atari information is essential for my move generation algorithm
(to disallow suicides, etc)
question: does
All,
I completed a new, improved, still not perfect, but hopefully more portable
version of the bitmapgo mockup.
The 9x9 source will be send out separately as a reply. I am still cleaning
up the 19x19 version and send it later.
Some general observations and questions:
o drop-off in playout
Look for the attachment and thread starting here:
http://computer-go.org/pipermail/computer-go/2009-October/019672.html
On Fri, Dec 4, 2009 at 3:48 PM, Michael Williams
michaelwilliam...@gmail.com wrote:
Very nice. Do you (or anyone) have the details of (Boon, 2009)
concerning arbitrarily
Welcome Aldric,
Not a frequent poster myself, here are two resources that you may find
useful.
1) an extensive library of articles related to computer-go is collected on
http://www.citeulike.org/group/5884/library
This list provides a wealth of articles tracing back many years and used to
be
Christian,
Would you care to provide some more detail on your implementation for the
playouts? Your results are very impressive. At 19x19 Go using bit-boards,
your implementation is roughly 7x as fast as the bitboard implementation I
presented just a few weeks back, and also outperforms libEgo by
-error-1 [bitmap_t::is_one_bit]: 78
test-error-1 [bitmap_t::is_one_bit]: 79
test-error-1 [bitmap_t::is_one_bit]: 80
And then it crashes.
René van de Veerdonk wrote:
[I do not know what happens, but this is the second time the computer-go
archives miss the body. Maybe its the attachment. I
Zach,
I can't help the windowsiness, but thanks for taking a look already.
Popcounting I believe to be optimal for 32-bit only instructions, especially
since I would like to keep the intermediate byte-count to help speed up the
random pick function. There is a really neat trick to speed up the
efficient with
bitmaps as it requires cumbersome bit-scanning.
René
On Tue, Aug 25, 2009 at 6:09 PM, Mark Boon tesujisoftw...@gmail.com wrote:
2009/8/25 René van de Veerdonk rene.vandeveerd...@gmail.com:
Nonetheless, bitmap-go as a topic keeps resurfacing on this
mailing list every once
that
before). It may not be too hard to try 19x19 and just see what happens. I
may attempt this as a follow-up.
René van de Veerdonk
2009/8/23 David Fotland fotl...@smart-games.com
How much would you lose for 19x19 board? A board representation is not
very interesting unless it scales to 19
:
2009/8/24 René van de Veerdonk rene.vandeveerd...@gmail.com:
David,
Confession: I have not tested 19x19. As you have noted, and others before
you over the years, a 19x19 board does not fit in one but three 128-bit
registers and there would be a rather big penalty as a result, perhaps
14 matches
Mail list logo