Path: utzoo!utgpu!news-server.csri.toronto.edu!rpi!zaphod.mps.ohio-state.edu!pacific.mps.ohio-state.edu!linac!uwm.edu!ogicse!orstcs!tesla.orst.EDU!tgd
From: tgd@tesla.orst.EDU (Tom Dietterich)
Newsgroups: comp.ai
Subject: Re: HI-Q game
Message-ID: <1991Apr29.192045.1852@lynx.CS.ORST.EDU>
Date: 29 Apr 91 19:20:45 GMT
References: <1991Apr24.055054.16724@cunixf.cc.columbia.edu>
Sender: @lynx.CS.ORST.EDU
Reply-To: tgd@tesla.orst.EDU (Tom Dietterich)
Organization: Department of Computer Science, Oregon State Univ.
Lines: 18
Nntp-Posting-Host: tesla.cs.orst.edu

This puzzle has been solved using an elegant machine learning method
by Glenn Iba:

Learning by Discovering Macros in Puzzle Solving.  Proceedings of the
Ninth International Joint Conference on Artificial Intelligence
(IJCAI-85), 1985 Vol. 1 640-642.

Iba's program selectively learns macros by noting when a simple
hill-climbing heuristic fails to give accurate estimates of 
the quality of board positions.


Thomas G. Dietterich
Department of Computer Science
Dearborn Hall, 303
Oregon State University
Corvallis, OR 97331-3102
503-737-5559