[computer-go] Floating komi

[Don Dailey]

steve uurtamo wrote:
> why doesn't someone simply try this and post the results,
> if they think that it would help?
>
>   
If someone would do this scientifically I would be all for it.   But I
am a bit of a pessimist about this.   I can easily imagine someone
trying it at reporting good results when the program is actually
weaker.     They would say,  "yeah,  I tried it and it worked pretty
good!"    or "Yeah,  I looked at some games and it was playing much better."

I would be satisfied if someone implemented it,  reported a 500 game
self-test sample and concluded that it didn't hurt the program
measurably and show a few examples of how it improved the moves
cosmetically,   perhaps even comparing both version with specific
positions. 

I wouldn't be opposed to fixing my program if I couldn't measure a
weakening and got better looking moves in the ending.   

- Don


> s.
>
>
> On Thu, Mar 6, 2008 at 8:30 AM, Don Dailey <drdailey at cox.net> wrote:
>   
>>  Christoph Birk wrote:
>>  > On Mar 5, 2008, at 11:58 AM, Don Dailey wrote:
>>  >>> Don Dailey wrote:
>>  >>>>  not assuming that MC plays the best move.   The problem isn't the
>>  >> assumptions I am making, but the assumptions others are making,  that
>>  >> it's NOT playing the best move.    You want to apply a fix to all
>>  >> positions without really knowing which positions are a problem.
>>  >
>>  > One last time: Nobody suggested a one fix for all positions/problems.
>>  > The "floating komi" was suggested to guide the UCT search along
>>  > certain lines of play during specific (close!) endgame positions.
>>  When I said all positions I meant all games.    You expect to apply this
>>  to all winning and losing positions in every game, not just specific ones.
>>
>>  - Don
>>
>>
>>
>>  >
>>  > Christoph
>>  >
>>  > _______________________________________________
>>  > computer-go mailing list
>>  > computer-go at computer-go.org
>>  > http://www.computer-go.org/mailman/listinfo/computer-go/
>>  >
>>  _______________________________________________
>>  computer-go mailing list
>>  computer-go at computer-go.org
>>  http://www.computer-go.org/mailman/listinfo/computer-go/
>>
>>     
> _______________________________________________
> computer-go mailing list
> computer-go at computer-go.org
> http://www.computer-go.org/mailman/listinfo/computer-go/
>
>