TY - GEN
T1 - The impact of noise on iterated prisoner's dilemma with multiple levels of cooperation
AU - Chong, Siang Yew
AU - Yao, Xin
PY - 2004
Y1 - 2004
N2 - Real world dilemmas rarely involved just two choices and perfect interactions without mistakes. In extending the realism of the Iterated Prisoner's Dilemma (IPD) game, prior evolutionary approaches included intermediate choices or mistakes (noise). This study takes a step further using a co-evolving population of neural networks playing the IPD game with both intermediate choices and noise. Several issues will be addressed, which include the evolution of cooperation and the evolutionary stability in the presence of noise and more choices. Our experimental study shows that noise has a negative impact on the evolution of cooperation, but could improve, surprisingly, the evolutionary stability.
AB - Real world dilemmas rarely involved just two choices and perfect interactions without mistakes. In extending the realism of the Iterated Prisoner's Dilemma (IPD) game, prior evolutionary approaches included intermediate choices or mistakes (noise). This study takes a step further using a co-evolving population of neural networks playing the IPD game with both intermediate choices and noise. Several issues will be addressed, which include the evolution of cooperation and the evolutionary stability in the presence of noise and more choices. Our experimental study shows that noise has a negative impact on the evolution of cooperation, but could improve, surprisingly, the evolutionary stability.
UR - https://www.scopus.com/pages/publications/4344617926
M3 - Conference contribution
AN - SCOPUS:4344617926
SN - 0780385152
SN - 9780780385153
T3 - Proceedings of the 2004 Congress on Evolutionary Computation, CEC2004
SP - 348
EP - 355
BT - Proceedings of the 2004 Congress on Evolutionary Computation, CEC2004
T2 - Proceedings of the 2004 Congress on Evolutionary Computation, CEC2004
Y2 - 19 June 2004 through 23 June 2004
ER -