[ View Thread ] [ Post Response ] [ Return to Index ] [ Read Prev Msg ] [ Read Next Msg ]

BGonline.org Forums

XG training and NN question

Posted By: Timothy Chow
Date: Sunday, 1 August 2010, at 5:33 p.m.

In Response To: XG training and NN question (Tom Keith)

Suppose you train a bot on Snake. Then you don't need to "force the bot off its normal track" in order to get it to play a lot of deep backgames.

It's certainly true that one cannot hope to cover all possible positions. However, deep backgames, while rare, are not that rare. It's not like only one in a billion games ever turns into a deep backgame. We've all played such games. The argument from big numbers doesn't sound very convincing to me.

Now, it's possible that neural nets aren't the right algorithm for superbackgames. Then the programming challenge would be greater.

Messages In This Thread

 

Post Response
Your Name:
Your E-Mail Address:
Subject:
Message:

If necessary, enter your password below:

Password:
 

 

[ View Thread ] [ Post Response ] [ Return to Index ] [ Read Prev Msg ] [ Read Next Msg ]

BGonline.org Forums is maintained by Stick with WebBBS 5.12.