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

BGonline.org Forums

Using two bots instead of a longer rollout: effect on confidence in result

Posted By: Timothy Chow
Date: Saturday, 22 December 2012, at 1:11 a.m.

In Response To: Using two bots instead of a longer rollout: effect on confidence in result (leobueno)

Tom has explained the math assuming the two bots are identical.

You might get some additional confidence from using two different bots if the bots have different strengths and weaknesses. XG and GNU play very similarly in most positions so the extra benefit here is usually low. They may differ sharply in certain unusual positions that neither bot understands, but then the rollouts probably don't mean anything anyway.

However, if XG 3-ply evaluation chooses a different play from GNU 2-ply evaluation but both bots agree upon rollout, then I would be inclined to derive some extra confidence from the rollout agreement. I don't think there's any good way of quantifying this extra confidence, though.

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.