Re: [Bug-gnubg] bug in 3 ply equities

[Øystein Johansen]

Hugh Sconyers wrote:
>  
> Hi
>  
> There is something strange going in this position.
>  
> side on roll has:
> 1-24, 1-23, 1-13, 2 each 9 8 7 6 5 4 pc = 138
>  
> side not on roll has 1- 22
>  
> it is dmp.

 GNU Backgammon  Position ID: AAAgYNs2BKAAAA
                 Match ID   : cAklAAAAAAAA
 +13-14-15-16-17-18------19-20-21-22-23-24-+     O: gnubg
 | X                |   |             X  X | OOO 0 points
 |                  |   |                  | OOO
 |                  |   |                  | OOO
 |                  |   |                  | OOO
 |                  |   |                  | OO
v|                  |BAR|                  |     1 point match (Cube: 1)
 |                  |   |                  |
 |                  |   |                  |
 |                  |   |                  |
 |          X  X  X |   | X  X  X          |     Rolled 21
 |          X  X  X |   | X  X  X  O       |     0 points
 +12-11-10--9--8--7-------6--5--4--3--2--1-+     X: user

Like this?

In this situation odd-ply and even-ply does match each other very well. 
The esponation is simply that the crashed net is not very well trained 
in these position type. The crashed net still needs a bit more training. 
To me it lloks like the net understands the pos when it's vied from O 
side, but overestimates X winning chances when it's viewing the position 
from X's viewpoint.

Dear Hugh,
If you have reference positions like this, where you know the right(ish) 
outcome, the project would be very happy add this to the training database.

I can't say that the crashed net is the "worst" trained network, but 
it's simplest to find positions gnubg doesn't handle correctly in the 
crashed position class.

-Øystein