|
From: | Frank Berger |
Subject: | [Bug-gnubg] New positions for training database |
Date: | Fri, 21 Jul 2006 10:17:59 +0200 |
Another source of interesting positions would be to generate games fromthe Nackgammon start position. With more chequers back, there will be lots of interesting holding games, as well as a decent share of backgames, which are another challenging area.Frank Berger once told me that he tried to train a net from nackgammon starting position. IIRC the new net turned out to play slightly weaker in backgames than the original one, but I don't have details about his experiment.
I benched the new NG net against the fully trained BG net.The result were that the NG-net were wearker, but in NG it did a little better. When the new NG matured, it still did better in NG than in BG. The funny thing were that the difference in playing strength between playing NG and BG for the old net and the new NG-net get smaller and smaller. When the new NG net was fully trained the difference between the nets were approx. 1point/100 cubeless games. When I did that in 2002 or so, the HW was much slower, so maybe I try it again later.
For GNU it may work better, because of the different training methods (BGBlitz uses straight TD(lambda)-Training). I would guess it's worth a try.Interesting. That's a surprise to me. I would have thought there would be benefits. I haven't played much nackgammon myself, so I don't knowhow games evolve. Maybe with both sides having four men back, reasonablytimed one-sided backgames rarely evolve.
Another approach might start from prototype holding games and backgames such as found in Kit Woolsey's Encyclopaedia. The idea being that theseare common positions, so it is useful to have plenty of data for accurate training.
If you enter the positions, could you please send me a copy? ciao Frank
[Prev in Thread] | Current Thread | [Next in Thread] |