Le mardi 12 février 2008, David Schneider-Joseph a écrit :
On Feb 11, 2008, at 8:42 PM, Don Dailey wrote:
David Schneider-Joseph wrote:
By definition,
komi is proportional to the value of moving first. Likewise, by
definition, your skill is the amount of value you get out of a move.
Here is a 2 ply tree of all the CGOS games. The winning percentage now
is ALWAYS from the point of view of the player making the given move.
Some interesting factoids:
1. E5 looks like a winning move, but if white responds C5 (the fourth
popular move) then White wins more games.
2.
Here are the statistics on all the CGOS games through January 2008 with
the winning percentages. This is from the point of the view of the
player making the move.
The most popular move is E5 and it also is the only move with a positive
score. I consider all games regardless of how strong or
Improved view and more games. After 1336 games black still wins. This
is sorted by frequency of occurrence, so we know that e5 c4 c5 (or
equivalent) is the most popular move for cgos.
I think I should nega-max the percentages instead of showing it just
from white's point of view. So the
Ok, I don't know if this is fully debugged, but I created a program
that reads SGF files, places statistics in a canonical hash and then
walks the tree, only showing canonical versions of each move.
I will make several improvements later such as displaying moves in order
of success or
On 12-feb-08, at 17:39, Christoph Birk wrote:
All games that white won W+0.5 would reverse to B+0.5 if you
lowered the komi by 1 pt.
Unless you used some MC bot, then W would still win by 0.5 :)
___
computer-go mailing list
On Tue, 12 Feb 2008, Magnus Persson wrote:
Hence in the normal situation komi must be 9 in order to make the 45/36 split
on the board become jigo. At least in area scoring. A simple empirical thing
is to check the results of CGOS 9x9 right now. All white vicories are even
numbers + 1/2 i.e.
It's a little less because a few more games were played when I compile
that data, but not very many. Still, that is pretty substantial.
All the games begin with E5 by the way.
I suppose the next step is to compile win statistics for various
combinations. Here is a start, the winner is the
On Tue, 12 Feb 2008, Magnus Persson wrote:
I corrected this sensei page to give komi 9 for 7x7 and added a link to the
sgf file John Tromp provides with the analysis.
Thanks.
Similarily one find that in very simple games on 9x9, but where the moves are
good solid shape white almost always
That's 41% of the 206 games that begin with E5 {G5,C5,E7,E3}
On Feb 12, 2008 1:38 PM, Don Dailey [EMAIL PROTECTED] wrote:
This pattern doesn't appear to often:
5 E5 G5 G4
6 E5 C5 C4
8 E5 C5 C6
12 E5 E7 D7
12 E5 E7 F7
13 E5 G5 G6
14 E5 E3 D3
15 E5 E3
This pattern doesn't appear to often:
5 E5 G5 G4
6 E5 C5 C4
8 E5 C5 C6
12 E5 E7 D7
12 E5 E7 F7
13 E5 G5 G6
14 E5 E3 D3
15 E5 E3 F3
(assuming I transposed these correctly)
- Don
Olivier Teytaud wrote:
46 E5 C5
By the way, mogoRelease with
Hi, here comes the simple explanation, but some more data as indicated
below might of course empirically overturn this.
There are 81 points to split.
If black has 44 and white 37 points then white komi 7 there is jigo.
But when black get 1 point more white also get one point less. The
On Feb 12, 2008 1:01 PM, Don Dailey [EMAIL PROTECTED] wrote:
Here are frequencies that it plays each response to E5 out of 761 games:
1 E5 B4
1 E5 B6
1 E5 D8
1 E5 F8
1 E5 H4
1 E5 H6
2 E5 B5
2 E5 F2
3 E5 E4
3 E5 H5
5 E5 E8
6
Magnus,
I'm getting an odd result with Mogo. I am running games at a fairly
decent level with 6.5 and 8.5 komi to see what will happen.
At 6.5 komi we get this:
* B = 289 = 0.58859
W = 202 = 0.41141*
At 8.5 komi we get this:
* B = 383 = 0.52610
W = 345 = 0.47390
46 E5 C5
By the way, mogoRelease with moderate computation times often plays
E5-C5-C6, and this third move C6 is very weak (at least I've
been told so :-) ).
___
computer-go mailing list
computer-go@computer-go.org
Jason House wrote:
Other games that come to mind:
Chess (covered elsewhere, I assume)
http://www.talkchess.com/forum/viewforum.php?f=7
Checkers
Abalone http://en.wikipedia.org/wiki/Abalone_(board_game)
http://en.wikipedia.org/wiki/Abalone_%28board_game%29
I expect checkers and
Jason House wrote:
I've never much cared for forums. Does this one have features that
allow me to use it like a mailing list (e.g. notifications of new
messages, ability to respond quickly and easily in response to e-mail
notifications, etc...)
Yes. You can click on subscribe forum at the
On Feb 12, 2008 10:14 AM, Jason House [EMAIL PROTECTED] wrote:
If you would like to have a subforum created on a topic related to game
programming, then don't hesitate to ask, and I'll add a new subforum. It
is not my intention to be a competitor to established mailing lists and
forums, so
On Feb 12, 2008 8:49 AM, Rémi Coulom [EMAIL PROTECTED] wrote:
Hi,
I am now a little interested in developing a program to play the game of
Hex, and I started to search the web for some information. I found that
for many games played in the Computer Olympiad, such as Hex or Amazons,
there is
Christoph Birk wrote:
On Feb 11, 2008, at 9:39 PM, Don Dailey wrote:
My feelings on this seem to match at least one source:
Look here:http://senseis.xmp.net/?Komi
Here is an excerpt:
It is widely believed that the correct komi is independent of board size
for all but the
9.5pt komi is unreasonable. I agree with Don that perfect game value
will probably turn out to be 7pts, though I'm keeping an open mind that
it may be 6pts. I'd be surprised if it was 8pts, though that could just
mean I've been analyzing the wrong openings :-).
On 9x9 with Chinese rules
On Tue, Feb 12, 2008 at 9:03 AM, Darren Cook [EMAIL PROTECTED] wrote:
9.5pt komi is unreasonable. I agree with Don that perfect game value
will probably turn out to be 7pts, though I'm keeping an open mind that
it may be 6pts. I'd be surprised if it was 8pts, though that could just
mean
22 matches
Mail list logo
