[computer-go] UCT caveat (was in Explanation to MoGo paper wanted)

[Jacques Basaldúa]

Brian Slesinsky wrote:

> And this would mean that a position where black is in trouble 
> would look stronger than in a random playout (due to black 
> playing well only for this kind of situation) which would make 
> it harder to tell which positions are actually good.

> Or in general, an improvement in play that only works for some
> positions will tend to make those positions look good, and make it
> hard to tell which positions actually are good.

That's what I mean. The defense favors one player (the one in 
danger) more than the other and these positions get a wrong
evaluation. That is dangerous and, in general, will weaken the
program. Maybe in a particular situation it is a good idea.
Sometimes breaking the rules is a good idea. ;-)

I like this example because it sounds very reasonable and it is not 
obvious that it is breaking the rules (the unbiasedness rule), but 
it is. 

Jacques.