Games: Planning and Learning
Papers from the 1993 Fall Symposium
Susan Epstein and Robert Levinson, Program Cochairs
Technical Report FS-93-02. Published by The AAAI Press, Menlo Park, California
This technical report is available in book format.
Please Note: Abstracts are linked to individual titles, and will appear in a separate browser window. Full-text versions of the papers are linked to the abstract text. Access to full text may be restricted to AAAI members. PDF file sizes may be large!
Contents
Go-Moku Solved by New Search Techniques / 1
L. V. Allis, H. J. van den Herik, M. P. H. Huntjens, University of Limburg and Vrije Universiteit, Netherlands
Designing a Computer Opponent for War Games: Integrating Planning, Knowledge Acquisition and Learning in WARGLES / 10
Michael Hieb, David Hille, and Gheorghe Tecuci, George Mason University
td-Gammon, A Self-teaching Backgammon Program, Achieves Master-Level Play / 19
Gerald Tesauro, IBM, TJ Watson Research Center
Toward an Analysis of Forward Pruning / 24
Stephen J. Smith and Dana S. Nau, University of Maryland
New Approaches to Moving Target Search / 30
Stan Melax, University of Alberta
Best First Minimax Search: First Results / 39
Richard Korf and David Chickering, UCLA
How a Bayesian Approaches Games Like Chess / 48
Eric Baum, NEC Research Institute
Re-Examination of Brute Force Search / 51
Jonathan Schaeffer, Paul Lu, Duane Szafron, Robert Lake, University of Alberta
Games with Imperfect Information / 59
Jean R. S. Blair, David Mutchler and Ching Liu, University of Tennessee
A Pruning Algorithm for Imperfect Information Game / 68
Michael Van Lent and David Mutchler, University of Tennessee
A Comparison of Probabilistic Search and Weighted Heuristics in a Game with Incomplete Information / 77
Steven Gordon, East Carolina University
Strategic Planning for Imperfect-Information Games / 84
Stephen J. Smith and Dana S. Nau, University of Maryland
The Integration of Visual-Cues into a Multiple-Advisor Game-Learning Program / 92
S. L. Epstein, J. Gelfand, J. Lesniak and P. Abadie, Hunter College, CUNY and Princeton University
Memory-Based Approaches to Learning to Play Games / 101
Chris Atkeson, MIT
Derivative Evaluation Function Learning Using Genetic Operators / 106
David H. Lorenz and Shaul Markovitch, Technion
Toward a Theory of Well-Guided Search / 115
Susan L. Epstein, Hunter College and CUNY
The Interaction Between Perceptual and Cognitive Processes in a Distributed Problem-Solving Task / 123
Jiajie Zhang, The Ohio State University
Learning Team Plays in a Competition for Foods between Ant Colonies as Autonomous Agents / 132
Masao Kubo and Yukinori Kakakazu, Hokkaido University, Japan
Learning Models of Opponent’s Strategy in Game Playing / 140
David Carmel and Shaul Markovitch, Technion
A Strategic Metagame Player for General Chesslike Games / 148
Barney Pell, Cambridge University
Exploiting the Physics of State-Space Search / 157
Robert Levinson, UC Santa Cruz