Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: Hello from Edmonton (and on Temporal Differences)

Author: David Rasmussen

Date: 00:27:45 07/31/02

Go up one level in this thread


On July 30, 2002 at 22:43:36, James Swafford wrote:

>
>Hey everyone.  I'm at an AAAI conference in Edmonton.  It's ironic (to me)
>that it's been mentioned here recently that Edmonton is a hive of computer
>chess enthusiasts.  I don't know if that's true (what's a "hive"? :-), but
>there are certainly a few...
>
>Now to my question.  I asked Jonathon Schaeffer today (who is a really
>nice guy, IMO) some questions about his experience with TD learning
>algorithms.  He's (co?)published a paper entitled (something like)
>"Temporal Difference Learning in High Performance Game Playing."  I
>thought the title was a bit misleading, because he focused on checkers.
>Checkers programs have much smaller evaluation fuctions than chess
>programs, obviously.  I asked him if he thought the TDLeaf(Lambda)
>algorithm had potential in high calibre chess.  (Yes, yes, I know
>all about Knightcap... but that wasn't quite "high" calibre.)
>He responded with a very enthusiastic "yes".  He said "I'll never manually
>tune another evaluation function again."
>
>A natural follow up question (which I also asked) is -- then why isn't
>everyone doing it??  I don't _believe_ (and maybe I'm wrong about this)
>that any top ranked chess programs use it.  His response was simply:
>"There's a separation between academia and industry."  Schaeffer stated
>that perhaps the programmers of top chess programs don't believe in
>the potential of temporal difference algorithms in the chess domain.
>Or, perhaps, they don't want to put the effort into them.
>
>I believe Crafty is the strongest program in academia now.  If not,
>certainly among the strongest.  So, Bob -- have you looked at TDLeaf
>and found it wanting?  It's interesting (and perplexing) to me that
>paper after paper praises the potential of TDLeaf, but it's _yet_ to
>be used in the high end programs.  Knightcap was strong, but it's
>definitely not in the top tier.
>
>Maybe Tridgell/Baxter quit to soon, and Knightcap really could've been
>a top tier program.  Or maybe the reason nobody is using TD is because
>it's impractical for the large number of parameters required to be
>competitive in chess.  Or maybe Schaeffer was right, and the commercial
>guys just aren't taking TD seriously.
>
>Thoughts?
>

I can only say that I have thought about adding this to Chezzz for a long time,
but haven't gotten around to doing it yet. Now Chezzz certainly isn't high
calibre, but I'm sure that, given the patterns that I have decided to score in
Chezzz, that the actual parameters of the values could be "better". I wouldn't
be surprised to see a 100 point rating increase. Also, it would make it a lot
simpler to try new patterns.

/David



This page took 0 seconds to execute

Last modified: Thu, 15 Apr 21 08:11:13 -0700

Current Computer Chess Club Forums at Talkchess. This site by Sean Mintz.