Naslov
GENETIC ALGORITHM APPLIED TO THE STOCHASTIC ITERATED PRISONER’S DILEMMA

Autori
Hižak, Jurica

Vrsta, podvrsta i kategorija rada
Sažeci sa skupova, neobjavljeni rad, znanstveni

Skup
BaSoTi 2016

Mjesto i datum
Talin, Estonia, 01.08.2016. - 02.08.2016

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Podatak o recenziji nije dostupan

Ključne riječi
Evolution of Cooperation, Iterated Prisoner’s Dilemma, TFT, genetic algorithm

Sažetak
The evolution of cooperation among bacteria may be studied via discrete replicator dynamics, but studying more complex organisms may require different approach such as genetic algorithm. A more realistic model would imply mutation and recombination between strategies, which could preserve genetic variability. In this paper we present a stochastic IPD with sexual reproduction whereby each reactive strategy (p, q) is represented by 10-bits chromosome. Five bits encode the probability p, while the remaining five bits serve to encode the probability q. Having made such model, we found that population indeed goes through the cycles of cooperation and exploitation. The recombination of genetic material, constantly giving new strategies, drives the population from one extreme to another, between ALLD and TFT

Izvorni jezik
Engleski

Znanstvena područja
Matematika, Interdisciplinarne prirodne znanosti, Računarstvo, Informacijske i komunikacijske znanosti

POVEZANOST RADA