Another example I found is the impressive Valkyria program.   Version
2.7 won 92% of it's games,  more than even the top rated greenpeep0.5.1.

However,  the average rating of Valkyria's opponents was only 1722.  
This is quite a difference.   So Valkyria is rated only 2222 compared to
greenpeep 2621 despite the fact that it wins more!   

Of course 2222 is still impressive and Valkyria is number 17  out of all
the programs that have played over 200 games  (over 200 of them.)  

- Don




Don Dailey wrote:
> Let me refer you to the bayeselo web site,  this is not my work but due
> to Rémi Coulom <http://remi.coulom.free.fr/>.    I am simply using his
> software to build the table:
>
>        http://remi.coulom.free.fr/Bayesian-Elo/
>
> The score is simply how well the program scored against it's totally
> opposition.   It's not particularly meaningful because stronger players
> tend to have stronger opponents, still it is interesting statistic to
> have available.     When a program like MoGo scores 95% despite the fact
> that it is paired mostly against strong players,  it is impressive.
>
> The opponent is the average rating of the opponents of each game.    So
> when you combine score and opponent you have something very useful.   
> For instance:
>
>     greenpeep0.5.1 with an ELO of 2621 scored 90% against an average
> opponent of 2043
>     MoGo_G3.4ae    with an ELO of 2571 scored 95% against an average
> opponent of 2009
>
> So even though MoGo won more of it's games,   it's average opponent was
> weaker and this was enough to give greenpeep about 50 more ELO rating
> points.     It's more impressive to score 90% against a strong field
> than 95% against a somewhat weaker field.  
>
> - Don
>
>
>
>
> Jason House wrote:
>   
>> What is the proper way to interpret the score and opponent columns?
>>
>> On Dec 9, 2007 7:30 PM, Don Dailey <[EMAIL PROTECTED]
>> <mailto:[EMAIL PROTECTED]>> wrote:
>>
>>     I just put up the improved hall of fame page.  
>>
>>     I'm using the values Rémi suggests and the values look more in
>>     line with CGOS.
>>
>>     Also, FatMan-1 is fixed at 1800 instead of FatMan and there are
>>     links to the crosstable pages.
>>
>>
>>           * http://cgos.boardspace.net/9x9/hof.html*
>>
>>
>>     I'm not sure how often I will update the page - probably just once
>>     per month right at the beginning of the month. 
>>
>>     - Don
>>
>>
>> ------------------------------------------------------------------------
>>
>> _______________________________________________
>> computer-go mailing list
>> computer-go@computer-go.org
>> http://www.computer-go.org/mailman/listinfo/computer-go/
>>     
>
>   
_______________________________________________
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/

Reply via email to