[Top][All Lists]

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [gnugo-devel] GNU Go 3.3/3.5

From: Daniel Bump
Subject: Re: [gnugo-devel] GNU Go 3.3/3.5
Date: Fri, 26 Apr 2002 10:12:55 -0700

> Dan wrote:
> > These are all good ideas. (2), (6) and (7) seem projects for later.
> > Actually for (2) I think it is important to eventually do this
> > but there seem to be more urgent things first, (6) may be on 
> I think you underestimate the value of (2).

No, I don't! We are referring to:

> 2. Rewrite strategical evaluation to a strict before move/after move
>    comparison. This has to use: moyo size, eye shape, esacpe values, ...

I am convinced believe that the only best way to get a realistic
valuation is to place the stone on the board and evaluate the
resulting position. In complicated positions especially this
seems the best way to proceed.

This is why I did the metamachine experiments.  Remember that
the metamachine generated the top ten moves, tries the top two
and runs estimate_score to find out which one improves the board
position the most.


reply via email to

[Prev in Thread] Current Thread [Next in Thread]