Title :
How important is your reputation in a multi-agent environment
Author :
Yao, Xin ; Darwen, Paul J.
Author_Institution :
Sch. of Comput. Sci., Birmingham Univ., UK
fDate :
6/21/1905 12:00:00 AM
Abstract :
Most work on the evolutionary approach to the iterated prisoner´s dilemma (IPD) game uses a binary model where the choice of each player can only be cooperation or defection. However, we rarely commit ourselves to complete cooperation or defection in the real world. The paper examines the continuous IPD game and similarities and differences between the discrete and continuous games. The paper also studies the issue of reputation of a player, following Nowak and Sigmund´s (1998) work, and how it affects the evolution of cooperation. This study differs from Nowak and Sigmund´s in that players in a population can have more than two levels of cooperation (or even continuous). The players are also changing all the time under the influence of selection, crossover and mutation. We think that this is a more realistic model of the evolution of society in the real world
Keywords :
game theory; learning (artificial intelligence); multi-agent systems; continuous game; cooperation; discrete game; evolutionary approach; iterated prisoner´s dilemma; multi-agent environment; reputation; society; Australia; Computer science; Evolutionary computation; Genetic mutations; Humans; Missiles; Peer to peer computing; Sorting;
Conference_Titel :
Systems, Man, and Cybernetics, 1999. IEEE SMC '99 Conference Proceedings. 1999 IEEE International Conference on
Conference_Location :
Tokyo
Print_ISBN :
0-7803-5731-0
DOI :
10.1109/ICSMC.1999.825324