[Top][All Lists]

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[Bug-gnubg] Holding game improvement?

From: Øystein Johansen
Subject: [Bug-gnubg] Holding game improvement?
Date: Sun, 08 Jun 2003 19:02:58 +0200
User-agent: Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.2.1) Gecko/20021130

Hi all!

At GammOnLine there's several discussions of GNU Backgammon, and in one of them Neil suggests that GNU needs some improvement in holding game evaluations. I actually think he has a point.

"Holding games are very very common in BG and if GNU were a bit better with the cube in them I feel it definately would be the best bot out there."

Just to start a discussion I'm mailing some of my opinions of how this can be done. As I see it there's two possible techniques to get better holding game evaluations.

1. Train the current net further.

2. Add a new neural net for handling holding games only.

The first method is very simple in theory. Can we add some holding game positions to a training database and run a couple of epochs? The problems will be to verify that this new net wil play stonger than the previous net. We may risk that the net forgets some of the skill it has learned previous training sessions. Will the database of reference positions report this.

The second method is a bit trickier. First we need a definition of holding game. Then we must train this net, and then we may have the problem of the discontinuities of the nets.

This is just some lines to start a discussion and to hear the different opinions here at the list. Joseph?


reply via email to

[Prev in Thread] Current Thread [Next in Thread]