I haven't seen anything to that effect on the list. By the nature of UCT,
it should focus in on a fight if it is critical to the outcome of the game.
I haven't seen any documentation of explicitly restricting the scope of an
MC search, but the concept makes sense to me.
On 4/16/07, [EMAIL PROTEC
I haven't gotten to read through your paper as carefully as I'd like yet,
but I do have a few observations that may be of benefit to other readers on
the list... Mostly observation of assumptions used in the paper.
1. A max tree is used instead of minimax
2. Rewards can be more than just 1 or 0 (
On 4/25/07, Remi Munos <[EMAIL PROTECTED]> wrote:
> 3. The goal is to find the optimal leaf rather than the optimal subtree.
I'm not sure to understand this comment. Actually the goal is to find a
close-to optimal play at the root level. Thus finding a close-to-optimal
min-max leaf achieves tha
On 4/25/07, Remi Munos <[EMAIL PROTECTED]> wrote:
> When I did sit down and read the paper for real, I saw that both of
those
> things were just building up the support for the BAST algorithm. (a) is
to
> justify accepting a higher regret (in exchange for better worst case
> performance).
well
On 5/1/07, Joel Veness <[EMAIL PROTECTED]> wrote:
My intuition suggests that b) is the better approach, but I know that
a) works much better in computer chess.
Does anyone know why a works much better in computer chess? Does the
benefits of a correct guess (and thinking more deeply than the
On 5/7/07, Peter Drake <[EMAIL PROTECTED]> wrote:
When I
look through the children of A and count a total of one playout, it
seems natural that I should update the playout count for A:
I would normally try to save all simulation results, but I can certainly see
the value of forcing invariant
While I can't talk specifically about UCT, I believe that transposition
tables are one of the easiest and most profound speed ups you can do for a
program. The answer really depends on the depth you're searching.
At two moves ahead, all results are unique. At 4 moves ahead, it's a 75%
savings.
On 5/11/07, Brian Slesinsky <[EMAIL PROTECTED]> wrote:
> Going along with this, the numbers won't add up (although I don't know
> if that is important.) In other words, if you do 10,000 simulations at
> the root, all grandchildren will add up to more (due to transpositions.)
> If you propogate
On 5/14/07, Hideki Kato <[EMAIL PROTECTED]> wrote:
Thanks Nick, but the result tables are swapped.
I think it's just the board sizes - Open is marked 13x13, but should have
been 9x9
(Vice versa for formal division)
___
computer-go mailing list
compu
I found the detailed results page tough to read. Here's a quick key on
how to read it. Maybe it's overkill.
For those trying to read the results... Taking the last line from test 1,
"explore_rate = 1 - ego_base wins 62.7 + 3.8 % games (158 ames)"
The first part "explore_rate = 1 - ego_base" is
How do you handle n_i = 0 in equation 1.2? I'd assume that if a heuristic
says a move is really bad (H_B = 0), then you'd want to avoid simulations
for a while.
Also, has mango experimented with other related strategies for a soft
transition?
In my own mathematical recreation, I came up with a
Rémi Coulom wrote:
to Magnus: If you consider the example of section 2.2: 1,2,3 wins
against 4,2 and 1,5,6,7. The probability is
P=c1c2c3/(c1c2c3+c4c2+c1c5c6c7). For this example:
N1j=c2c3,B1j=0,M1j=c2c3+c5c6c7,A1j=c4c2
N2j=c1c3,B2j=0
N3j=c1c2,B3j=0
N4j=0,B4j=c1c2c3
I will add this example to t
Chaslot G (MICC) wrote:
p_hat = (w_i + n_h*H_B)/(n_i+n_h)
Interesting... But then how do you compute n_h in practice
The mathematical derivation is based on estimating an a-priori
probability distribution. In theory, one simply needs to run MC
simulations for a wide variety of heur
Widening sounds more natural to me.
On 5/24/07, Chaslot G (MICC) <[EMAIL PROTECTED]> wrote:
Dear all,
I did experiments on 19x19 Mango with 25000 simulations per move, against
GnuGo 3.6 level 0.
Without progressive unpruning, Mango wins 2.9% (250 games), and with
progressive unpruning, Ma
If I remember right, the original SimpleBot by Aloril was in python. There
was also a spin off called PyBot. Cheating and looking at
http://www.weddslist.com/kgs/names.html, I believe the spin off was by Deren
Dohoda... who also helped with SimpleBot. The two bots probably represented
different
On 5/25/07, Peter Drake <[EMAIL PROTECTED]> wrote:
I was under the impression that grafting was used more often for attaching
a foreign branch (e.g., to make a pear grow on an apple tree) than for
repair. I'm probably wrong about this.
That's the same that I've heard. It may be the norm tha
As I get into the home stretch of rewriting the core of my bot, I want
to add a monte carlo player. I've realized that picking a random move
to play is non-trivial since it's such a key element in playout speed.
An array of legal positions has easy lookup, but may not be easy to
maintain...
?ukasz Lew wrote:
Jason, can You tell me why You don't want to use libego instead?
Actually this is open question to all comp-go readers.
Is libego too complicated? Do You have problems with compilation?
Or You are not comfortable with the GNU license? Any other reason?
I probably have a lot o
Don Dailey wrote:
Lukasz Lew does something far more sophisticated and very fast using the
concept of pseudo liberties which you might want to look into.
Both pseudo liberties as well as disjoint set chain tracking. Curiously
enough, they're both things I independently came up with when I
Darren Cook wrote:
Jason House also mentioned "hard coding to a set board size", I think
libego can be used at least up to 19x19, just by changing the
"board_size" setting in board.cpp (it also supports hexagonal boards).
Or did you mean being able to make one binary for all
Don Dailey wrote:
I remember that conversation and the negative response. But to be fair
to the ones who were negative, you presented this as an evaluation
feature that could be calculated quickly, not as a pure performance
optimization. The negative response was in response to the suggestion
In looking at the paper again, I cheated and looked at the graphics and the
conclusion. For those of us who are concerned with comparison to UCT, I
believe that it's off the chart to the left, but would likely match the
plateau. Initially, I was looking at the plot as if it was time series
data,
On 6/5/07, Peter Drake <[EMAIL PROTECTED]> wrote:
On a multithreaded program like Orego (running on a multicore machine), it
moves the nontrivial random number generation out of the synchronized part
of the program and into the threads.
I'm surprised to hear this. Do you have a single random
On 6/5/07, Don Dailey <[EMAIL PROTECTED]> wrote:
But if you are taking the vacant points out it is probably not
too biased as you say.
But what I do is pretty fast. Always choose a random point but
keep shrinking the list. When a point is occupied move it out
of the way so it's never selected
On 6/6/07, Rémi Coulom <[EMAIL PROTECTED]> wrote:
> I wonder if other people had thought about this before...
>
> Álvaro.
Yes, I did it in the beginning. But I found that it is faster to divide
by more than two. Currently, I keep the probability of the whole board,
each line, and each point. It
On 6/7/07, Don Dailey <[EMAIL PROTECTED]> wrote:
I noticed there is almost no activity on the 19x19 server.
I can run an old version of housebot (0.4) on the server. It does 1-ply
search with heuristics, so its rating would be quite low, but it's almost
zero CPU load. It can run 24/7 minus
On 6/7/07, Don Dailey <[EMAIL PROTECTED]> wrote:
I noticed there is almost no activity on the 19x19 server.
BTW - A google search for CGOS gives http://cgos.boardspace.net/ as the top
hit. That page has a link to http://cgos.boardspace.net/9x9/index.html but
not to the 19x19 go server. I kn
On 6/7/07, Peter Drake <[EMAIL PROTECTED]> wrote:
Chaslot G.M.J.B., Winands M.H.M. Winands, Uiterwijk J.W.H.M., van denHerik
H.J., and Bouzy B. Progressive strategies for Monte-Carlo tree
search.
1.3.1: Add heuristic value (divided by # of playouts) to UCT value.
While I haven't done any form
For simplicities sake, let's say I do a pure 0-ply and 1-ply monte carlo
search. If the color to move is my color, I'd expect the 0-ply search to
give me a more conservative winning percentage than the 1-ply search (since
I'd pick the best child rather than average the children together).
Similar
the color to move was. Does
that help?
Jason House wrote:
For simplicities sake, let's say I do a pure 0-ply and 1-ply monte carlo
search. If the color to move is my color, I'd expect the 0-ply search to
give me a more conservative winning percentage than the 1-ply search (sinc
Magnus Persson wrote:
Quoting Jason House <[EMAIL PROTECTED]>:
Does anyone have any data on just how optimistic or pessimistic the
results
would be? I'd like to use some heuristics that inherit winning
percentages
from a parent node to bias the expected winning percentage of th
Magnus Persson wrote:
Quoting Jason House <[EMAIL PROTECTED]>:
Looking at a single color, the winning percentage seems to shift by
0.2 to 0.4%... About what I'd expect to see. What confuses me though
is how to interpret the jump back and forth as the color changes
(about 8%
Joshua Shriver wrote:
Anyone have a list and URL's for all of the open source and/or free
engines?
-Josh
I'm not too sure about open source or not for most bots, but here are
some places to look:
http://www.weddslist.com/kgs/names.html
http://senseis.xmp.net/?KGSBots
Here are the ope
On 6/15/07, Phil G <[EMAIL PROTECTED]> wrote:
JIT didn't solve everything - the managed memory management in Java (and
C#) has overheard which JIT can not always optimized away, for example.
The D programming language website argues in favor of garbage collection...
Even claiming that it cou
On 6/15/07, Don Dailey <[EMAIL PROTECTED]> wrote:
I think D keeps improving. The gcc version is slower anyway, so I
haven't bothered with it but my understanding is that they have made a
lot of optimizations since we last discussed the performance of D on
this group. Of course I haven't tested
On 6/15/07, Erik van der Werf <[EMAIL PROTECTED]> wrote:
So far, Steenvreter has never played on CGOS. I'm very busy with work,
so it will take a while before I have time to put it up for some
games. Also to be honest, I'm not really that interested. I guess CGOS
is nice if you have no other way
rake
http://www.lclark.edu/~drake/ <http://www.lclark.edu/%7Edrake/>
On Jun 16, 2007, at 9:02 AM, Jason House wrote:
On 6/15/07, Erik van der Werf <[EMAIL PROTECTED]> wrote:
> So far, Steenvreter has never played on CGOS. I'm very busy with work,
> so it will take a
Darren Cook wrote:
Down the years my excuse for working on computer go has been as a
test-bed for learning new technologies. This time it is taking advantage
of multi-core.
Interesting article here [1]:
http://www.linux-mag.com/launchpad/business-class-hpc/main/3538
I'm too lazy to make a
Darren Cook wrote:
I've been toying with the idea of having a set of playout algorithms and
allowing black and white to choose different algorithms in that playout.
(The idea came from trying to think how I could apply genetic
algorithms to UCT playouts.)
Here's how it would work. Assume you ha
Open Division Round 1
- You mention AyaBot2 joining it's game with CrazyStone. That should be
HBotSVN.
- "Printing name and version number" happens when the bot crashes, kgsGtp
terminates, and a script automatically reconnects the bot, and the cycle
repeats. It may be better to say that the Simo
On 7/9/07, Nick Wedd <[EMAIL PROTECTED]> wrote:
In message
<[EMAIL PROTECTED]>, Jason
House <[EMAIL PROTECTED]> writes
>Open Division Round 5
>- I personally thought the IdiotBot/HBotSVN game had an interesting
>end position. Despite the extreme weakness of HBo
On 7/9/07, Nick Wedd <[EMAIL PROTECTED]> wrote:
>Also, HB04 does not show up in the names of programs page. Of course,
>the housebot logins are piling up:
>HouseBot: Intended for stable version of HouseBot. It's the only
>ranked account.
>HB04 - Very old HouseBot 0.4 - Extremely fast play based
On 7/9/07, Jason House <[EMAIL PROTECTED]> wrote:
On 7/9/07, Nick Wedd <[EMAIL PROTECTED]> wrote:
> >Also, HB04 does not show up in the names of programs page. Of course,
> >the housebot logins are piling up:
> >HouseBot: Intended for stable version of Hou
On 7/9/07, Don Dailey <[EMAIL PROTECTED]> wrote:
I think the common formula is 100 ELO per stone? I think we could
start with this guess (or a better one) and after a few weeks of play we
could do a statistical analysis to see if things are as they should be.
Then we could make any adjustments
On 7/9/07, Phil G <[EMAIL PROTECTED]> wrote:
HouseBot (C++)
http://housebot.sourceforge.net/index.php/Main_Page
More precisely, the HouseBot SGF code is available at
http://housebot.svn.sourceforge.net/viewvc/housebot/branches/0.5/housebot/src/sgf/
It's freely available under the GPL v2 lic
On 7/10/07, chrilly <[EMAIL PROTECTED]> wrote:
I have no finished a plain vanilla 9x9 Suzie-UCT Version. The UCT-tree is
stored in a Hashtable. I am interested who else uses this approach.
The reason for using a hashtable was: I was too lazy to implement an
explicit tree. At least at 9x9 I have
On 7/12/07, chrilly <[EMAIL PROTECTED]> wrote:
Why is it not possible to establish uniform rules in Go?
I'm curious... How does the rule sets affect how people play the game of
go? I personally find territory scoring more interesting. 90% of my reason
for that is because the game ends soon
On 7/12/07, Phil G <[EMAIL PROTECTED]> wrote:
But there are only two drawbacks with this approach. One, it only works as
a result of a customized GTP command. Sometimes I want it to display
debugging information data while the GTP command is still executing (or
maybe as an addition to an existin
On 7/12/07, Robert Jasiek <[EMAIL PROTECTED]> wrote:
Jason House wrote:
> I personally find territory scoring more interesting. 90% of my
> reason
> for that is because the game ends sooner... I don't have to go filling
dame
> (open spaces between chains of opposing col
On 7/12/07, Phil G <[EMAIL PROTECTED]> wrote:
Jason wrote:
> I'd also be willing to support slight variants to SGF that use positions
> such as C4 instead of wacky things that don't match the notation
> everyone else uses and vary depending on the board size.
Anders Kierulf's SmartGo program
On 7/12/07, Nick Wedd <[EMAIL PROTECTED]> wrote:
In message
<[EMAIL PROTECTED]>, Jason
House <[EMAIL PROTECTED]> writes
>On 7/12/07, chrilly <[EMAIL PROTECTED]> wrote:
> Why is it not possible to establish uniform rules in Go?
>
>I'm curious... How does
On 7/12/07, Robert Jasiek <[EMAIL PROTECTED]> wrote:
Jason House wrote:
> KGS does a fine job with unfilled dame.
Any server that violates the rules during scoring does not do a "fine"
job. KGS violates whichever Japanese rules.
It's probably already clear that I
On 7/12/07, Robert Jasiek <[EMAIL PROTECTED]> wrote:
Jason House wrote:
> I mean that the
> resulting marking of who's territories is who's matches what I would
have
> done if I stopped at that point and scored the game.
Occasionally, KGS fails here. See rec.games.go
On 7/13/07, Don Dailey <[EMAIL PROTECTED]> wrote:
I agree with you on this as far as etiquette is concerned. In on-line
computer vs computer games resignation is "honorable" but against humans
a computer should simply play fast - up the level of it's ability.A
strong computer player can pas
On 7/16/07, Don Dailey <[EMAIL PROTECTED]> wrote:
I made some slight changes to the server as well as incorporating Remi's
suggestion:
1. Server will not send "play b resign" or "play w resign"
Is there any way that the server will tell the engine that the game is
over? Since my engine p
The US Go Congress begins in less than two weeks. I have two questions:
1. If you plan to attend, which days will you be there?
2. Will you be competing? (Not with a bot)
3. Which days are most convenient for a gathering of developers?
As for myself, I'm not competing or attending beyond whate
'm kind of a newbie do you have a URL for the event? What is it like?
-Josh
On 7/16/07, Jason House <[EMAIL PROTECTED]> wrote:
> The US Go Congress begins in less than two weeks. I have two questions:
> 1. If you plan to attend, which days will you be there?
> 2. Will you be
On 7/16/07, Don Dailey <[EMAIL PROTECTED]> wrote:
The client itself knows the game is over, it's just not transmitted to
the engine.
One way to deal with this is to make the client send a quit command. I
think some program would like to quit and be restarted before and after
each game.
As a
yikes!*
and that's just the registration fee.
On 7/16/07, Jason House <[EMAIL PROTECTED]> wrote:
The US Go Congress begins in less than two weeks. I have two questions:
1. If you plan to attend, which days will you be there?
2. Will you be competing? (Not with a bot)
3. Which days are
On 7/16/07, Don Dailey <[EMAIL PROTECTED]> wrote:
So what I will do is implement cgos_gameover which gives a reason.
I will also honor the kgs-gameover version when the cgos version is not
supported.
The gtp spec asks that you do cgos-gameover instead of cgos_gameover. The -
separates the c
Joshua Shriver wrote:
Curious what game rules does CGOS use? I noticed when viewing some
engines will pass pass and end, while some will play all the way till
everything is pretty much filled in which I believe is Chinese rules.
I'm a little confused over the rules so perhaps I'm not stating it
c
On 7/17/07, Don Dailey <[EMAIL PROTECTED]> wrote:
I will reconsider doing: cgos-playerinfo white FatMan 1800
What about making it explicitly about the opponent?
cgos-opponent white FatMan 1800
___
computer-go mailing list
computer-go@computer-go.o
Thanks for the documentation. I have a few questions.
Looking at only the four neighbors to detect eye-like points seems like it
could leave many false eyes and allow captures of dangling chains. Is there
any mechanism to avoid this problem in the play of the bot?
I'll have to think more about
On 7/20/07, Peter Drake <[EMAIL PROTECTED]> wrote:
On Jul 20, 2007, at 7:23 AM, Jason House wrote:
Thanks for the documentation. I have a few questions.
Looking at only the four neighbors to detect eye-like points seems like it
could leave many false eyes and allow captures of da
On 7/20/07, Peter Drake <[EMAIL PROTECTED]> wrote:
On Jul 20, 2007, at 8:04 AM, Jason House wrote:
> I thought he was using the disjoint set! I'll recheck. Well
> written disjoint sets average out to nearly O(1) operations for
> everything.
Yes -- O(log* n) to be precise
On 7/20/07, Ian Osgood <[EMAIL PROTECTED]> wrote:
My beginner UCT program (http://www.quirkster.com/forth/fgp.html)
uses bitboards because it is very simple to express the rules of Go
using bit operations. However, a mailbox board which contains
references into string objects which incrementally
On 7/20/07, [EMAIL PROTECTED] <[EMAIL PROTECTED]> wrote:
Jason House said:
> Thanks for the documentation. I have a few questions.
>
> Looking at only the four neighbors to detect eye-like points seems like
> it could leave many false eyes and allow captures of dangling chai
On 7/16/07, Jason House <[EMAIL PROTECTED]> wrote:
The US Go Congress begins in less than two weeks. I have two questions:
1. If you plan to attend, which days will you be there?
2. Will you be competing? (Not with a bot)
3. Which days are most convenient for a gathering of deve
n that.
I forget how far it is, but I'm 2-3 hours away. I will drive up that day
and drive home that night. A meeting start time in the 12-5 window is
doable for me.
On 7/20/07, Jason House <[EMAIL PROTECTED]> wrote:
On 7/16/07, Jason House <[EMAIL PROTECTED]> wrote:
>
ROTECTED]>
To: Jason House <[EMAIL PROTECTED]>
References: <[EMAIL PROTECTED]>
Hi Jason,
Thank you very much for your email and for your interest in attending the 2007
US Go Congress.
I apologize in the delay in responding to your email. We are still working out
some o
BotSVN
- Name of bot: HouseBot 0.6.2
- Authors: The HouseBot development team
- Division: Open
- My name: Jason House
On 7/26/07, Nick Wedd <[EMAIL PROTECTED]> wrote:
The August 2007 KGS computer Go tournament will be on the first Sunday
in August, August 5th, in the Asian even
On 7/27/07, Nick Wedd <[EMAIL PROTECTED]> wrote:
>
> >I'd like to register HBotSVN for the open tournament. I forget why we
> >ran HB04 in the last tournament as well, but let me know if that's
> >desired for this tournament.
>
> It's entirely up to you. I have a slight preference for more entrant
Over the last 4 months or so, I've been building up the documentation at
http://housebot.sourceforge.net/index.php/Agile_Development
I've tried to keep it at a fairly high quality level by polling for
feedback from friends and family and hunting down tools for graphical
documentation. I think
Since my rewrite, I don't consider my bot (HouseBot) to be too far
along... It barely knows how to do more than play a legal game of go
(it does 1-ply monte carlo)
The class goban tracks the board state, checks for legality, etc... It
can be found here:
http://housebot.svn.sourceforge.net/v
On behalf of Peter Christopher [EMAIL PROTECTED], I am forwarding this message.
It looks like there's is another candidate for the meeting tomorrow. It may
just be Peter and I there, but we'll see. My current plan for tomorrow is to
try and make my way to the student union around 5. We'll s
As usual, minor corrections and nit-picks:
Formal division - I initially interpreted "3 active participants" to mean
that break was removed from the tournament, but then realized this was not
the case after reading the next sentence. Maybe some kind of wording change
would clarify that?
Open d
I believe the original paper used 32 simulations from each point as part
of its pattern... But the spirit of it (as I understand it) really is
to bias the 1-ply move selection at the start of MC searches. (In Crazy
Stone, just 3x3 patterns are used at deeper ply?)
elife wrote:
I think CrazyP
cgosview9x9 shows game 101909, MindReader(1953) vs. MonteGNU(2116), to
in progress with no stones ever played in it.
http://cgos.boardspace.net/9x9/standings.html seems to show both
opponents playing in a different active game (along with many others).
It looks like the web page shows a different
, Don Dailey <[EMAIL PROTECTED]> wrote:
> I haven't been watching it very closely because I've been out of town
> for a while.
>
> I restarted the server, let me know if it looks like there is still a
> problem.
>
> - Don
>
>
> On Mon, 2007-08-20 at 14:10 -
Thanks for continuing to maintain such a nice service for the computer
go community.
I too will be tracking down a bug today... CGOS seems to have
highlighted at least one severe problem in my bot.
On 8/21/07, Don Dailey <[EMAIL PROTECTED]> wrote:
> On Tue, 2007-08-21 at 13:20 -04
Has anyone verified "Hb04 now refused to proceed with the game,
neither agreeing nor disagreeing about which stones were alive"? At the
start of the tournament, HB04 supported genmove and "final_status_list
dead", but not kgs-genmove_cleanup. HB04 played to what it considered
the end of the
On 9/11/07, Nick Wedd <[EMAIL PROTECTED]> wrote:
>
> In message <[EMAIL PROTECTED]>, Don
> Dailey <[EMAIL PROTECTED]> writes
>
> >Who has the best Go programs at 19x19 level? I think David Fotland is
> >only 2 Dan and his is one of the best. I know the old handtalk program
> >was written by a v
I am more than willing to provide a binary version of my program if someone
else provides the operator and (refundable) entrance fee. While I doubt my
weak program would get best of the year, if it did win, I'd be fine with
giving the extra $$ to whoever paid the entrance fee.
On 9/13/07, Ray Tay
I know I'm only wading in the kiddie pool of computer go with my 1-ply bots,
but I think I may have found a useful enhancement to monte carlo.
HouseBot supports three 1-ply search modes:
1plyMC - Uniform sampling
1plyShuffle - Uniform sampling with monte carlo transposition reuse
1plyUCT - N
ently.
On 9/14/07, Chris Fant <[EMAIL PROTECTED]> wrote:
>
> Does it defeat it based on number of samples taken or time allotted per
> turn?
>
> On 9/14/07, Jason House <[EMAIL PROTECTED]> wrote:
> > I know I'm only wading in the kiddie pool of computer go
ove of interest) += fractional game
if (random game is is win)
num wins (move of interest) += fractional game
// Note that variance of the estimate increases by (0.5 * fractional
game)^2
}
}
On 9/14/07, Brian Slesinsky <[EMAIL PROTECTED]> wrote:
>
> Can you e
On 9/14/07, Jason House <[EMAIL PROTECTED]> wrote:
> // Note that variance of the estimate increases by (0.5 * fractional
> game)^2
I should say that the variance of "wins" increases by that amount. The
estimate of winning percentage will be computed as wins / s
I'm curious - What is ReadyFreddy?
http://senseis.xmp.net/?ComputerGoServerdoes not list it. I do see
ReadyToGo. If it is, the description says 512
simulations. Over 81 moves, that seems like almost nothing... 6 sims per
move. Does it instead mean 512 sims per candidate move? That seems to mak
>
> ReadyFreddy and ReadyToGo are just AnchorMan running at a very fast
> level.
>
> - Don
>
>
>
>
> On Fri, 2007-09-14 at 14:30 -0400, Jason House wrote:
> > I'm curious - What is ReadyFreddy?
> > http://senseis.xmp.net/?ComputerGoServer does not
I found scrolling messages of "irregular response from server" or feeding
negative amounts of time left to the engines
22:54:05S->C genmove b -1189810108880
22:54:05C->E time_left b -1189810109 0
Using the viewer, it looks like the open games are not continuing. I
believe CGOS is down.
_
foreach(simplePosition xp, color xc; firstColor){
if (xc == nextMoveColor)
sims[xp] = sims[xp] + 1;
}
}
Jason House wrote:
I'm guessing that 110 means libego v0.110 (the latest pos
Don Dailey wrote:
This appears to be my exact logic.
That's a good start :)
Also, before we get too deep into this stuff, thanks for your help.
I can imagine many places where you might be doing something wrong.
1. Are you sure you are scoring the final game correctly including
elife wrote:
> 2. Do you include passes in the random games? You should not.
>
No passes are allowed in the random games. If the random move
generator
says to pass it means no legal moves are available and the game
gets scored.
Hi,
I am confused with why passed a
Rémi Coulom wrote:
Jason House wrote:
Yeah. An eye point is defined as an empty point where all four
neighbors are the same chain. This prevents weak combos of false
eyes, but does allow it to miss one kind of life.
Do you mean that your program would fill black eyes there:
#.#O.
.##OO
steve uurtamo wrote:
? This sounds like a really very very bad idea. But I may have
misunderstood.
Nah, you understood correctly.
ouch. it seems like you're forcing your eyes to be on the 2nd line
or above and all living groups to have stones on the 3rd
line or above.
right?
Down again...
Jason House wrote:
I found scrolling messages of "irregular response from server" or
feeding negative amounts of time left to the engines
22:54:05S->C genmove b -1189810108880
22:54:05C->E time_left b -1189810109 0
Using the viewer, it looks like the op
On 9/17/07, steve uurtamo <[EMAIL PROTECTED]> wrote:
>
> >> Yeah. An eye point is defined as an empty point where all four
> >> neighbors are the same chain.
>
> where "all four" gets modified to "all three" or "all two" on the first
> line
> or corner respectively?
Right
won't you miss any
On 9/17/07, Don Dailey <[EMAIL PROTECTED]> wrote:
>
> Another way to test this, to see if this is your problem, is for ME to
> implement YOUR eye definition and see if/how much it hurts AnchorMan.
>
> I'm pretty much swamped with work today - but I may give this a try at
> some point.
>
I'd be in
efinitions).
While I think the alternate eye definitions helped, I don't think they
accounted for more than 100-200 ELO
vs ego110_allfirst
orig= 33/46 = 71%
#1 = 17/20 = 85%
#2 = 16/18 = 89%
vs gotraxx-1.4.2a
orig=N/A
#1 = 2/8 = 25%
#2 = 3/19 = 16%
On 9/17/07, Jason House <[EMAIL PROTECTED]&
Method #1 - Don't play in that spot if the "4" neighbors match your color
and it'd be a suicide play for the opponent to play in that spot.
Method #2 - Don't play in that spot if the "4" neighbors match your color
and either...
It's a corner/edge and no diagonals are an enemy stone
Or it's a c
301 - 400 of 660 matches
Mail list logo
