Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: About head or tail (was Upon scientific truth - the nature of informati

Author: Ed Schröder

Date: 08:26:52 07/17/00

Go up one level in this thread


On July 17, 2000 at 09:25:27, Harald Faber wrote:

>On July 17, 2000 at 07:15:45, Ed Schröder wrote:
>
>>>>
>>>>In the early days of a chess programmer it is easy but when your program
>>>>is over 2300-2400 it becomes very difficult to judge a candidate program
>>>>improvement. Personally I use a main set of 70-100 positions (frequently
>>>>updated) which are tested manually first then a large set of >500 positions
>>>>that runs automatically that produces a detailed report and database of
>>>>every difference in regard to the previous version. If results are good
>>>>then an engine-engine 300 game match is done as described above. In a
>>>>later stadium (after a couple of program changes) some auto232 matches
>>>>are played. The latter is of minor importance (in respect to the changes)
>>>>as too much randomness is involved (book, learning). In the end my feeling
>>>>on a program change is the decisive factor.
>>>
>>>
>>>Anyway this is a very time spending task.
>>
>>That's why most of us need a full year if you know what I mean.
>
>
>I meant that I am surprised that it does not take longer...
>
>
>>>>>Playing 1000 games with tournament time control
>>>>>takes much too much time. Test positions don't reflect practical play.
>>>>>I really have no clue.
>>>>
>>>>>And that is why I always say thet the top-10 (!) programs
>>>>>play at equal strength.
>>>>
>>>>That's a bold statement.
>>>>
>>>>Ed
>>>
>>>I know. Prove me wrong. :-)
>>
>>How about a 10 game match....?
>>
>>Ed
>
>
>I am not talking of 10 games. And you explained yourself why even 100 games may
>give a wrong result.
>Or what exactly do you suggest?

I was joking in the spirit of this topic. I should have added a smiley.

Ed



This page took 0 seconds to execute

Last modified: Thu, 15 Apr 21 08:11:13 -0700

Current Computer Chess Club Forums at Talkchess. This site by Sean Mintz.