The Efficacy of Choosing Strategy with General Regression Neural Network on Evolutionary Markov Games

Shirin Kordnoori (Department of Computer Engineering-Artificial Intelligence, North Tehran Branch, Islamic Azad University, Tehran, Iran)
Hamidreza Mostafaei (Department of Statistics, Tehran North Branch, Islamic Azad University, Tehran, Iran.)
Mohammadmohsen Ostadrahimi (Department of Mathematics, Tehran North Branch, Islamic Azad University, Tehran, Iran)
Saeed Agha Banihashemi (Assistant Professor of Mathematics and Faculty Member of the Department of the school of international relations of Ministry of foreign affairs of the Islamic Republic of Iran)

IPTEK The Journal for Technology and Science
Vol 32, No 1 (2021)

Nowadays, Evolutionary Game Theory which studies the learning model of players,has attracted more attention than before. These Games can simulate the real situationand dynamic during processing time. This paper creates the Evolutionary MarkovGames, which maps players’ strategy-choosing to a Markov Decision Processes(MDPs) with payoffs. Boltzmann distribution is used for transition probability andthe General Regression Neural Network (GRNN) simulating the strategy-choosing inEvolutionary Markov Games. Prisoner’s dilemma is a problem that uses the methodand output results showing the overlapping the human strategy-choosing line andGRNN strategy-choosing line after 48 iterations, and they choose the same strate-gies. Also, the error rate of the GRNN training by Tit for Tat (TFT) strategy is lowerthan similar work and shows a better res