Mark,

Very cool that you were able to enjoy seeing an expert Tetris player emerge 
from your experiment. It sounds fun!

I worked on this very idea for Go about 5 years ago. I worked it pretty 
strongly, too. Unfortunately, I found it to be quite difficult and not very 
rewarding. There are so many issues with developing "strategies" that persist 
from generation to generation. Consider a human individual is both the genetics 
of the instance (phenotype) and the emergent effect of the accretions through 
high dynamic adaptations in the environment (unique to the individual's 
experience) combined with a lossy persistence system (dynamic and highly 
adaptive constructed/destructed rule system). These three things combine to 
make an individual operate.

I found that attempting to isolate any part of this to be a very unsuccessful 
tangent. And then finding ways to persist the isolated parts in a way that was 
adaptable to be way more difficult. I am not saying all three are required to 
be modeled to generate a Go player. I am saying, though, there is a unique 
balance in homo-sapien's emergent design that is going to take a VERY long time 
to grok and then model in software such that a highly capable Go player 
results. For now, I am betting that there will be vastly more progress on the 
pseudo-AI fronts like MC than on the actual attempts to roughly model human 
rules based cognition in variations of a genetic algorithm.


Jim





________________________________
From: Mark Boon <[email protected]>
To: [email protected]
Sent: Mon, April 26, 2010 7:03:03 PM
Subject: Re: [Computer-go] learning patterns for mc go

For a bit of a secondary project I've been doing the past few weeks I
made a self-learning Tetris program. To my own surprise this worked
extremely well. It 'grows' an expert player in just a few thousand
generations (a few days real time) starting from zero knowledge . And
it doesn't have any 'a priori' knowledge about the game, so it adjusts
when the (scoring) rules or playing conditions change. It works so
well, I was thinking this could very well apply to computer-Go
somehow.

Tetris is not Go of course. And also it's a single-player game, where
Go is a two-player game. So some adjustments about determining the
survivors and procreation may have to be made. It's a bit early for me
to divulge more details at this point. Also, this is research which my
current employer may not want to become public in great detail just
yet.

But based on my findings so far I can only encourage anyone who thinks
about making a self-learning Go program to go ahead and try.

Mark


On Mon, Apr 26, 2010 at 11:53 AM, Hendrik Baier
<[email protected]> wrote:
> Hello list,
>
> I am a Master's student currently working on his thesis about certain
> aspects of Monte-Carlo Go. I would like to pose a question concerning the
> literature - I hope some of you can help me out!
>
> My problem is that I can't find many papers about learning of MC playout
> policies, in particular patterns. A lot of programs seem to be using Mogo's
> 3x3 patterns, which have been handcoded, or some variation thereof. A lot of
> people have tried some form of pattern learning, but mostly to directly
> predict expert moves it seems, not explicitly optimizing the patterns for
> their function in an MC playout policy. Actually, I am only aware of
> "Computing Elo Ratings of Move Patterns in the Game of Go", where patterns
> have been learned from pro moves, but then also successfully used in an MC
> playout policy; and "Monte Carlo Simulation Balancing".
>
> Considering the huge impact local patterns have had on the success of MC
> programs, I would have expected more attention towards automatically
> learning and weighting them specifically for MC playouts. There is no reason
> why patterns which are good for predicting experts should also be good for
> guaranteeing diverse, balanced playout distributions. Have I missed
> something?
>
> Or how did your program come to its patterns? I'd be interested. Did you
> maybe even try learning something else than patterns for your playout
> policy?
>
> cheers,
> Hendrik
> _______________________________________________
> 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