I suspected you'd say something like this. ;) It is definitely on my list
of things to steal a few things from Michi. But maybe I'll start with
simpler and/or well defined things like RAVE or the hand picked MoGo 3x3
patterns. That way it's easy to see if I really screwed something
On Sat, Mar 28, 2015 at 11:51 AM, Petr Baudis pa...@ucw.cz wrote:
On Sat, Mar 28, 2015 at 11:45:48AM +0100, Urban Hafner wrote:
Good to know Petr! Where does the strength come from? Sophisticated
playouts or a search algorithm or both?
Frankly, I don't know for sure! The downside of
Urban Hafner:
cahmxpnnkr-ixqou4stxi_dfojfhj7j_qccj_duit6uqw4o8...@mail.gmail.com:
On Sat, Mar 28, 2015 at 11:51 AM, Petr Baudis pa...@ucw.cz wrote:
On Sat, Mar 28, 2015 at 11:45:48AM +0100, Urban Hafner wrote:
Good to know Petr! Where does the strength come from? Sophisticated
playouts or a
On Tue, Apr 7, 2015 at 12:56 PM, Petr Baudis pa...@ucw.cz wrote:
Hi!
On Tue, Apr 07, 2015 at 12:03:12PM +0200, Urban Hafner wrote:
Now that I have a bit of time again, what would be a good starting point
to
improve upon UCT and light playouts? RAVE definitely comes to mind, as
well
On Tue, Apr 7, 2015 at 12:20 PM, Hideki Kato hideki_ka...@ybb.ne.jp wrote:
For prior values in the tree, almost(?) all strong programs use Remi's
method these days.
http://remi.coulom.free.fr/Amsterdam2007/MMGoPatterns.pdf
Thank you! I will put that one on my reading list!
Urban
--
Blog:
Hi!
On Tue, Apr 07, 2015 at 12:03:12PM +0200, Urban Hafner wrote:
Now that I have a bit of time again, what would be a good starting point to
improve upon UCT and light playouts? RAVE definitely comes to mind, as well
as enhancing the playouts with heuristics like the MoGo 3x3 patterns.
Petr Baudis: 20150407105648.gp6...@machine.or.cz:
On Tue, Apr 07, 2015 at 07:20:37PM +0900, Hideki Kato wrote:
For prior values in the tree, almost(?) all strong programs use Remi's
method these days.
http://remi.coulom.free.fr/Amsterdam2007/MMGoPatterns.pdf
Do you mean all the strong programs do
On Apr 7, 2015, at 4:34 AM, Urban Hafner cont...@urbanhafner.com wrote:
I suspected you'd say something like this. ;) It is definitely on my list of
things to steal a few things from Michi. But maybe I'll start with simpler
and/or well defined things like RAVE or the hand picked MoGo 3x3
I suspected you'd say something like this. ;) It is definitely on my list
of things to steal a few things from Michi. But maybe I'll start with
simpler and/or well defined things like RAVE or the hand picked MoGo 3x3
patterns. That way it's easy to see if I really screwed something up.
On Tue, Apr 7, 2015 at 4:04 PM, Christoph Birk b...@obs.carnegiescience.edu
wrote:
On Apr 7, 2015, at 4:34 AM, Urban Hafner cont...@urbanhafner.com wrote:
I suspected you'd say something like this. ;) It is definitely on my
list of things to steal a few things from Michi. But maybe I'll
On Apr 7, 2015, at 7:16 AM, Urban Hafner cont...@urbanhafner.com wrote:
I wouldn't know, Christoph. My (and Igor's) bot is called Iomrascálaí. :P
It's running as the various Imrscl-XYZ bots on CGOS due to the username
length restriction and the fact that the current CGOS can't handle Unicode
It doesn't matter with simple UCT, but it's a huge difference when you
have more targeted playouts because you can find a subtree you really
like and spend 99%+ of your time exploiting that particular line (for
example, not dying in one move). I see Fuego re-use most of its existing
tree on a
On Tue, Apr 7, 2015 at 4:44 PM, Christoph Birk b...@obs.carnegiescience.edu
wrote:
thanks, I agree 1400 is about as far as simple UCT will get you.
My simple UCT implementation (myCtest-xxk-UCT) gets about
1200, but it does not do any adjustments to the number of playouts
per move depending
Can you put in the game description: really bad, only play if you're
patient and put in quicker time controls?
s.
On Mar 28, 2015 3:25 PM, hughperkins2 hughperki...@gmail.com wrote:
You can name name a specific opponent, and then your bot will play against
it.
Automatch works, but tends to
You can name name a specific opponent, and then your bot will play against it.
Automatch works, but tends to result in lots of people being forced to play
your bot, and then leaving the game, after the bot took ages to play in some
ridiculous location, which is kind of embarrassing :-P
I can offer you a factor of 2 speedup...
s.
On Mar 28, 2015 7:59 PM, hughperkins2 hughperki...@gmail.com wrote:
By the way, for mcts you dont need time controls. Each move takes the same
amount of time, since you just do n playouts, and choose n as you like.
I think my playouts took 2s,
Automatch is automatch: the other person doesnt choose to play rhe bot. ___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
By the way, for mcts you dont need time controls. Each move takes the same
amount of time, since you just do n playouts, and choose n as you like.
I think my playouts took 2s, which was enoufht for 4 playouts i suppose,
but it was in novemebr, dont remember clearly... It was obvious that
But my guess based on ad hoc tests during the development is that the
contribution of basic playout heuristics and RAVE+priors may be about
1:1 (with large pattern priors giving further extra boost).
I'll have to start reading papers on those concepts then, I guess. :)
Thanks Petr!
What does that translate to on CGOS 13x13? I have a hard time estimating how
strong my bot is in real terms. How exactly do you measure the strength?
Rated games on KGS?
Von meinem iPhone gesendet
Am 28.03.2015 um 12:33 schrieb Hugh Perkins hughperk...@gmail.com:
Still, it would be nice if
Well, what I did was connect my bot to kgs a few times, and watch as
it go repeatedly beaten by anything much better than 25k :-)
Normally, there's a few 'randombots' there to start with. Once you can
beat those (which is harder than it sounds, or it is if your program
has bugs, which mine did
Still, it would be nice if the computer could learn the heuristics
itself, by self-play.
Which is why my bot is still stuck on 25k rating :-D At least, that's
my excuse :-P
On Sat, Mar 28, 2015 at 7:18 PM, Urban Hafner cont...@urbanhafner.com wrote:
But my guess based on ad hoc tests during
On Sat, Mar 28, 2015 at 2:34 PM, Hugh Perkins hughperk...@gmail.com wrote:
Well, what I did was connect my bot to kgs a few times, and watch as
it go repeatedly beaten by anything much better than 25k :-)
Normally, there's a few 'randombots' there to start with. Once you can
beat those
On Sat, Mar 28, 2015 at 6:14 PM, Urban Hafner cont...@urbanhafner.com
wrote:
On Sat, Mar 28, 2015 at 2:34 PM, Hugh Perkins hughperk...@gmail.com
wrote:
Well, what I did was connect my bot to kgs a few times, and watch as
it go repeatedly beaten by anything much better than 25k :-)
On Sat, Mar 28, 2015 at 11:45:48AM +0100, Urban Hafner wrote:
Good to know Petr! Where does the strength come from? Sophisticated
playouts or a search algorithm or both?
Frankly, I don't know for sure! The downside of Michi's slowness is
that playtesting takes too many resources so
hi!
On Sat, Mar 28, 2015 at 11:30:37AM +0100, folkert wrote:
Because I read here that people can do 25k playouts per second while my
program can only do ~ 20 per second when doing full validity checks on
all steps.
Do you have a reference, some context for the 25K playouts?
Look
Good to know Petr! Where does the strength come from? Sophisticated playouts
or a search algorithm or both?
Von meinem iPhone gesendet
Am 28.03.2015 um 11:38 schrieb Petr Baudis pa...@ucw.cz:
hi!
On Sat, Mar 28, 2015 at 11:30:37AM +0100, folkert wrote:
Because I read here that people
Hi all,
I am working on a successor to Valkyria written in C++.
I agree with Petr here. I am still tweaking the basic engine and I have
still lot to fix. With a sloppy implementation initially I have 20 kpps
for 9x9 and 4.5 kpps for 19x19.
When the basic stuff is running I will build feature
Housebot was probably on the low end with 10kpps on 9x9. Libego was
probably the highest with 100kpps. I attribute some of the difference to
compiler maturity (D vs. C++). I don't know how rust will perform.
On Jan 14, 2015 3:14 AM, Urban Hafner cont...@urbanhafner.com wrote:
Hey everyone,
I'm
On Wed, Jan 14, 2015 at 01:26:44PM +0100, Urban Hafner wrote:
Hey Jason,
thanks. Rust is probably not very well optimised, yet. It hasn't even
reached 1.0 and there are still many language changes happening. But I
attribute the slowness to the fact that I'm not used to writing code in
On Wed, Jan 14, 2015 at 1:32 PM, Petr Baudis pa...@ucw.cz wrote:
Note that the mistake I did with Pachi is that I worked hard to optimize
the Go board (playout) code with minimal functionality to perform
a playout correct by the rules, only then discovering how much other
information I need
31 matches
Mail list logo
