Abstract | ||
---|---|---|
Making decisions under uncertainty remains a cen- tral problem in AI research. Unfortunately, most uncertain real-world problems are so complex that progress in them is extremely difficult. Games model some elements of the real world, and offer a more controlled environment for exploring meth- ods for dealing with uncertainty. Chess and chess- like games have long been used as a strategical- ly complex test-bed for general AI research, and we extend that tradition by introducing an imper- fect information variant of chess with some useful properties such as the ability to scale the amount of uncertainty in the game. We discuss the complex- ity of this game which we call invisible chess, and present results outlining the basic game. We mo- tivate and describe the implementation and appli- cation of two information-theoretic advisors, and describe our decision-theoretic approach to com- bining these information-theoretic advisors with a basic strategic advisor. Finally we discuss promis- ing preliminary results that we have obtained with these advisors. |
Year | Venue | DocType |
---|---|---|
2001 | AISTATS | Conference |
Citations | PageRank | References |
3 | 0.49 | 8 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
A. E. Bud | 1 | 3 | 0.49 |
David Albrecht | 2 | 356 | 36.66 |
Ann E. Nicholson | 3 | 692 | 88.01 |
I. Zukerman | 4 | 12 | 3.29 |