Re: The status of gnubg?

[Aaron Tikuisis]

I see, that's very interesting. I'll make sure not to use ctrl-g for skewed situations like this!

So the real problem is that it thinks that gammon chances are near 0 for a position like this, when in fact it is 25%:

​ GNU Backgammon  Position ID: h+sPAQD3rQEAAA

                 Match ID   : EAEAAAAAAAAE

 +12-11-10--9--8--7-------6--5--4--3--2--1-+     O: gnubg

 |                  |   |    O  O  O  O  O | O   0 points

 |                  |   |    O     O  O  O | O   On roll

 |                  |   |             O  O |    

 |                  |   |             O    |    

 |                  |   |             O    |    

^|                  |BAR|                  |    

 |                7 |   |                  |    

 |                X |   |                  |    

 |                X |   |    X           X |    

 |                X |   |    X           X |    

 |    X           X |   | X  X           X |     0 points

 +13-14-15-16-17-18------19-20-21-22-23-24-+     X: aaron (Cube: 1)

I'm not an expert but I'd think the NN should be able to learn this better - why not just try to train it more?

Is gnubg currently able to keep a database of its own 0-ply blunders? (Like, every time it does an evaluation, compare the higher-ply result with the 0-ply result and if the 0-ply errs by a large enough threshhold, add the position to the database.) If not, do you think it would be worth implementing this?

Best regards, Aaron

---

From: Øystein Schønning-Johansen <oysteijo@gmail.com>
Sent: October 19, 2020 9:26 AM
To: Aaron Tikuisis <Aaron.Tikuisis@uottawa.ca>
Cc: Joseph Heled <jheled@gmail.com>; Philippe Michel <philippe.michel7@free.fr>; bug-gnubg@gnu.org <bug-gnubg@gnu.org>
Subject: Re: The status of gnubg?

 

Attention : courriel externe | external email

On Mon, Oct 19, 2020 at 3:10 PM Aaron Tikuisis <Aaron.Tikuisis@uottawa.ca> wrote:

That is interesting, I did not realize that gnubg misplays race positions much. What are some examples?

 Here is a position I posted a few weeks ago. 

GNU Backgammon  Position ID: 960BAMCw+0MAAA
                 Match ID   : cAkAAAAAAAAA
 +13-14-15-16-17-18------19-20-21-22-23-24-+     O: gnubg
 |                  |   |    O  O  O  O  O | O   0 points
 |                  |   |    O     O  O  O | O  
 |                  |   |             O  O |    
 |                  |   |             O    |    
 |                  |   |             O    |    
v|                  |BAR|                  |     (Cube: 1)
 |                7 |   |                  |    
 |                X |   |                  |    
 |                X |   | X                |    
 |                X |   | X  X           X |     On roll
 |    X           X |   | X  X           X |     0 points
 +12-11-10--9--8--7-------6--5--4--3--2--1-+     X: oystein  

Money game and X to play. Try several rolls, like 52, 31 and 53 and... at 0-ply. What's the best move? 52: 6/1 6/4?

Of course, the evaluator reports 0.0 win, but since the gammons are incorrectly evaluated by the neural network, it makes ridiculous moves.

It looks like this is a common pattern in positions which are "skewed".

-Øystein