Computer Generation of Birds of a Feather Puzzles
Daniel Ziegler ’21, Gettysburg College
In this article, we describe a computer-aided design process for generating high-quality Birds of a Feather solitaire card puzzles. In each iteration, we generate puzzles via combinatorial optimization of an objective function. After solving and subjectively rating such puzzles, we compute objective puzzle features and regress our ratings onto such features to provide insight for objective function improvements. Through this iterative improvement process, we demonstrate the importance of the halfway solvability ratio in quality puzzle design. We relate our observations to recent work on tension in puzzle design, and suggest next steps for more efficient puzzle generation.
This is the publisher's version of the work. This publication appears in Gettysburg College's institutional repository by permission of the copyright owner for personal use, not for redistribution.
Version of Record
Neller, Todd and Daniel Ziegler. "Computer Generation of Birds of a Feather Puzzles." In Proceedings of the 33rd AAAI Conference on Artificial Intelligence (AAAI-19), Jan. 27-Feb 1, 2019, Honolulu, HI, 9693-9699. Palo Alto: AAAI Press.
Required Publisher's Statement
This article was originally made available on the publisher's website.