Neural Networks as a Unifying Learning Model for Random Normal Form Games
Adaptive Behavior (2011), vol. 19, no. 6, pp. 383 - 408, doi.org/10.1177/1059712311417636
36 Pages Posted: 12 Aug 2009 Last revised: 13 Aug 2012
Date Written: January 20, 2010
This paper models the learning process of a population of randomly-rematched tabula rasa neural network agents playing randomly generated 3 × 3 normal form games of all strategic types. Evidence was found of the endogenous emergence of a similarity measure of games based on the number and types of Nash equilibria, and of heuristics that have been found effective in describing human behavior in experimental one-shot games. The neural network agents were found to approximate experimental human behavior very well across various dimensions such as convergence to Nash equilibria, equilibrium selection and adherence to principles of dominance and iterated dominance. This is corroborated by evidence from five studies of experimental one-shot games, as the Spearman correlation coefficients of the probability distribution over the neural networks’ and human subjects’ actions ranged from 0.49 to 0.89.
Keywords: Behavioral game theory, Learning, Global games, Neural networks, Agent-based computational economics, Simulations, Complex adaptive systems, Artificial intelligence
JEL Classification: C45, C70, C73
Suggested Citation: Suggested Citation