Hi David

Do you know if there is a big difference between Gnugo 3.7.10 and 3.8?
That would explain a bit.

>From what I've seen/heard of Many Faces, I really can't compare the
number of playouts with my program. My program doesn't have much
"traditional" knowledge, unlike what I believe Many Faces has.

Thanx, I will keep trying different ideas.
--
Francois van Niekerk
Email: [email protected] | Twitter: @francoisvn
Cell: +2784 0350 214 | Website: http://leafcloud.com



On Fri, Dec 31, 2010 at 4:02 AM, David Fotland <[email protected]> wrote:
> It's a good start.  I haven't tested against gnugo on 9x9 for a long time so
> I tried a short test his afternoon.
>
> Many Faces, 1000 playouts per move, vs Gnugo 3.7.10, level 10.
> Many Faces won 75.9% of 3669 games (+-1.4% confidence level).
>
> It took me about 300 versions tested to get from 10% wins against gnugo in 3
> minute games to 90% wins against gnugo with 5K playouts, before I switched
> to 19x19.  Many things you try won't make your program better, but if you
> keep trying it will get much better.
>
> David
>
>> -----Original Message-----
>> From: [email protected] [mailto:computer-go-
>> [email protected]] On Behalf Of Jacques Basaldúa
>> Sent: Thursday, December 30, 2010 1:57 PM
>> To: [email protected]
>> Subject: [Computer-go] Oakfoam and ELO Features
>>
>> Hi Francois, Welcome
>>
>>
>>  > For reference I need about 100k playouts with
>>  > RAVE to get 50% winrate against GnuGo 3.8 L10.
>>
>> Yes that's more or less expected. At least before the
>> "big" improvements (yet to come ;-)
>>
>> In my case I do a lot of testing at 4x10000 because
>> the games are around 15 seconds long and I get fast
>> Elo confidence intervals. At that rate 40 K plyo/move
>> I get about 40-42% of wins against gnugo. This is more
>> or less consistent with a debugged barebones without
>> particular smarts (but with RAVE, without progressive
>> widening). I guess 40% at 40000 scales to 50% near
>> 100K but the exact point where I reach 50% has not
>> been studied as I expect it to be much lower in the
>> near future. (Optimistic)
>>
>>  > The next step is obviously to apply these to the
>>  > playouts. I am currently testing my program with
>>  > the ELO features in the playouts, but unfortunately
>>  > the preliminary results don't look good.
>>
>> That's exactly my experience! Although you do get
>> improvement with extend from atari/capture/distance to
>> prev heuristic.
>>
>> The Mogo and CrazyStone papers report improvement
>> "all features included" which is true because the
>> other ideas produce improvement, but they don't
>> give results for the patterns in isolation.
>>
>> I got a lot of improvement from Rémi's Bradley-Terry
>> ideas in move prediction (although with some
>> overlearning which I didn't care much about as
>> predicting moves is not my interest.) But neither
>> the naif values (times played/times seen) nor the
>> improved Bradley-Terry values are better in playouts
>> than uniform random. They are 158 CI(114..202) Elo
>> points worse!
>>
>> That is good and bad news. Why should uniform random
>> be the best?. Obviously it is not. But what humans
>> play lacks all the information about what they don't
>> play because it is obvious to them, but it is not
>> obvious to a "silly" playout policy.
>>
>> How to find good values for the patterns? (What I have
>> tried.)
>>
>> a. Use small patterns (3x3) with all non-ill-formed
>> patterns in the database. (Other databases have a value
>> for "unknown" this one shouldn't.)
>>
>> b. Classify patterns. I have done that in 40 classes.
>> This way you reduce the amount of degrees of liberty.
>> So your vector of gamma values is in R^40
>>
>> c. Then what? I really don't know. I have a "sort of
>> genetic algorithm". I like the idea that anything
>> changes at random, because the gammas are not
>> independent and this way the expected value of the
>> correlation is zero even under stochastic dependence.
>> Then I select the "best winners" and move my center of
>> gravity one little step in one or two classes of patterns
>> repeat the entire process. Then test to see if there
>> was improvement. A long process. I only won a little
>> in the first iterations. After tat fake improvement
>> that wasn't verified against uniform random.
>>
>> In all about 100 Elo points, less improvement than
>> the "humans patterns" do wrong. I guess best playouts
>> are a research area where there is room for improvement.
>>
>>
>> Jacques.
>>
>>
>>
>> _______________________________________________
>> Computer-go mailing list
>> [email protected]
>> http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
>
> _______________________________________________
> Computer-go mailing list
> [email protected]
> http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
>
_______________________________________________
Computer-go mailing list
[email protected]
http://dvandva.org/cgi-bin/mailman/listinfo/computer-go

Reply via email to