Re: [Bug-gnubg] Zadeh and mec mets

Hi Joseph,

Nice to hear from you too. Hope you are well. I think I may need to clarify my questions better. Here goes.

In gnu there are three mets available all related to the mec program but each one different as follows:

1. GnuBG 11 points – This is the excellent partially rolled out MET (to 11 points) which was extended by use of the mec26 MET to 25 points. (the gnu met file handles this by using a gnu met file populated by an array of equities)

2. Mec26 – a wholly mathematically derived MET derived from the mec program setting 26% as the gammon rate. Again the gnu met file is populated by the equity values at each score.

3. Mec – also available in gnu with values other than those listed above. The met file doesn’t include an array of numbers but instead includes parameters which look similar to deriving mec26. I am curious to know if the intention is to include this in gnu to enable the user to change setting as desired including skill advantage unsymmetrical mets, which would seem like an excellent idea. What ever was or is now the intention, the values you can read in gnu seem quite different from the mec26 program which is supposed to have the same properties. Something appears to have gone wrong.

I am particularly interested in the Zadeh (he now has had his name changed to Zada incidentally) as this was the first MET ever constructed (see link to paper below). I n see from correspondence viewable on the web that a lot of work was done by Joern in adapting the mathematical methodology and calibrating to replicate the values included in the paper (but without decimal points). Again, like the mec file, the gnu met file doesn’t include equity numbers but instead parameters which are I assume intended to replicate the values in the paper. As this method also includes skill advantage unsymmetrical mets – I assume yet again that the intention was to include this met working to default , or ideally to user adjustable settings. The trouble is all the great work seems to have gone to nothing because the values visible in gnu make scant comparison with values in the paper which I include below. Did someone spill virtual coffee over the default setting? This is one of the best METs around but the values visible in gnu would make it the worst in my opinion.

http://www.bkgm.com/articles/Zadeh/OnDoublingInTournamentBackgammon/

Could someone please advise me on how to run and use the mec program, which I managed to download but cant run – this would be very helpful.

I attach a few XG met files which can be read and edited using notepad. Feel free to adapt for use in gnu if you so desire.

Regards,

Rick

Here’s the Zadeh data integer values (getting a version with at least one decimal point will make it significantly more useful in determining correct cube action and gammon prices, etc)

[Current]

Name=Zada 1975

Version=1.0

Description="On Doubling in Tournament Backgammon" Norm Zada, 1975, assumes 25% gammon rate

[PostCrawford]

Size=15

Data="" 0.49 0.31 0.30 0.18 0.18 0.11 0.11 0.06 0.06 0.04 0.04 0.02 0.02 0.01

[PreCrawford]

Size=15

1=0.50 0.69 0.75 0.82 0.84 0.89 0.91 0.94 0.95 0.96 0.97 0.98 0.98 0.99 0.99

2=0.31 0.50 0.60 0.68 0.75 0.80 0.84 0.88 0.90 0.93 0.94 0.95 0.96 0.97 0.98

3=0.25 0.40 0.50 0.57 0.65 0.71 0.76 0.81 0.84 0.87 0.90 0.92 0.93 0.95 0.96

4=0.18 0.32 0.43 0.50 0.58 0.64 0.70 0.75 0.79 0.83 0.85 0.88 0.90 0.92 0.93

5=0.16 0.25 0.35 0.42 0.50 0.57 0.63 0.68 0.73 0.77 0.80 0.83 0.86 0.88 0.90

6=0.11 0.20 0.29 0.36 0.43 0.50 0.56 0.62 0.67 0.71 0.75 0.79 0.82 0.85 0.87

7=0.09 0.16 0.24 0.30 0.37 0.44 0.50 0.55 0.61 0.66 0.70 0.74 0.77 0.80 0.83

8=0.06 0.12 0.19 0.25 0.32 0.38 0.45 0.50 0.55 0.60 0.65 0.69 0.73 0.76 0.79

9=0.05 0.10 0.16 0.21 0.27 0.33 0.39 0.45 0.50 0.55 0.60 0.64 0.68 0.72 0.75

10=0.04 0.07 0.13 0.17 0.23 0.29 0.34 0.40 0.45 0.50 0.55 0.59 0.63 0.67 0.71

11=0.03 0.06 0.10 0.15 0.20 0.25 0.30 0.35 0.40 0.45 0.50 0.54 0.59 0.63 0.67

12=0.02 0.05 0.08 0.12 0.17 0.21 0.26 0.31 0.36 0.41 0.46 0.50 0.54 0.58 0.62

13=0.02 0.04 0.07 0.10 0.14 0.18 0.23 0.27 0.32 0.37 0.41 0.46 0.50 0.54 0.58

14=0.01 0.03 0.05 0.08 0.12 0.15 0.20 0.24 0.28 0.33 0.37 0.42 0.46 0.50 0.54

15=0.01 0.02 0.04 0.07 0.10 0.13 0.17 0.21 0.25 0.29 0.33 0.38 0.42 0.46 0.50

From: Joseph Heled [mailto:address@hidden
Sent: 22 June 2013 06:19
To: Rick Janowski
Cc: address@hidden
Subject: Re: [Bug-gnubg] Zadeh and mec mets

Hi Rick,

It has been a long time. The mec26 was obtained by first getting the post crawford probabilities from rollouts, then from the program mec.cc (i.e. "first principles"). I can't remember where the other tables came from :(

However, I remember running a fair number of rollouts and evaluations of specific positions with different equity tables, and was always surprised how little effect that had, if at all.

A position has to be very marginal in some sense if an equity table change changes the move or cube action.

It has been a while, so perhaps someone can take a fresh look and see if my observation above is correct or not - by examining on a much larger scale (which was not feasible at the time).

Alternatively, one can build an accurate table today based on rollouts alone, and compare it to the rest.

-Joseph

On 22 June 2013 02:39, Rick Janowski <address@hidden> wrote:

Hi,

I wanted to ask how the match equities for Zadeh and mec METs (mec not mec26) are handled in gnu – the met files have no array of probabilities so it looks like the computer calculates from first principles. If so something has gone badly wrong with the parameters because the Zadeh equities are often more than 3or 4% different than the values tabulated in his paper of 75. Checking those values in his paper I found that incredibly there was quite negligible error with the rolled out mets produced by Rockwell and Kazaross – less than 1% at all pre crawford scores in a 15 point match and when crawford and post crawford are also considered no error greater than 1.2%. Unfortunately the values you see in Gnu make it look like the worst MET of all.

Rick

_______________________________________________
Bug-gnubg mailing list
address@hidden
https://lists.gnu.org/mailman/listinfo/bug-gnubg

From:	Rick Janowski
Subject:	Re: [Bug-gnubg] Zadeh and mec mets
Date:	Sat, 22 Jun 2013 11:34:29 +0100