Title :
Sequential decision making using expert advice
Author_Institution :
Dept. of Electr. Eng., Stanford Univ., CA
fDate :
27 Jun-1 Jul 1994
Abstract :
Presents a theory for sequentially choosing decisions by combining the suggestions of a fixed number of experts. the author takes a game theoretic approach and attempts to do as well as the best expert under worst case assumptions. Surprisingly, it is possible to do as well as if one knows the statistics of the system in advance. The author applies these results to the problem of how to gamble on a sequence of letters drawn from a finite alphabet
Keywords :
decision theory; game theory; sequences; sequential estimation; expert advice; finite alphabet; gambling; game theoretic approach; letter sequence; sequential decision making; sequentially choosing decisions; statistics; worst case assumptions; Decision making; Game theory; History; Probability distribution; Statistics; Zinc;
Conference_Titel :
Information Theory, 1994. Proceedings., 1994 IEEE International Symposium on
Conference_Location :
Trondheim
Print_ISBN :
0-7803-2015-8
DOI :
10.1109/ISIT.1994.395001
