Interactive Learning in 2×2 Normal Form Games by Neural Network Agents

Physica A: Statistical Mechanics and its Applications (2012) - Volume 391, Issue 22, Pages 5557–5562

13 Pages Posted: 13 Aug 2012

See all articles by Leonidas Spiliopoulos

Leonidas Spiliopoulos

Max Planck Society for the Advancement of the Sciences - Max Planck Institute for Human Development

Date Written: August 12, 2012

Abstract

This paper models the learning process of populations of randomly rematched tabula rasa neural network (NN) agents playing randomly generated 2x2 normal form games of all strategic classes. This approach has greater external validity than the existing models in the literature, each of which is usually applicable to narrow subsets of classes of games (often a single game) and/or to fixed matching protocols. The learning prowess of NNs with hidden layers was impressive as they learned to play unique pure strategy equilibria with near certainty, adhered to principles of dominance and iterated dominance, and exhibited a preference for risk-dominant equilibria. In contrast, perceptron NNs were found to perform significantly worse than hidden layer NN agents and human subjects in experimental studies.

Keywords: Game theory, Learning, Neural networks, Agent-based computational economics, Simulations, Complex adaptive systems

JEL Classification: C45, C70, C73

Suggested Citation

Spiliopoulos, Leonidas, Interactive Learning in 2×2 Normal Form Games by Neural Network Agents (August 12, 2012). Physica A: Statistical Mechanics and its Applications (2012) - Volume 391, Issue 22, Pages 5557–5562. Available at SSRN: https://ssrn.com/abstract=2128247

Leonidas Spiliopoulos (Contact Author)

Max Planck Society for the Advancement of the Sciences - Max Planck Institute for Human Development ( email )

Lentzeallee 94
D-14195 Berlin
Germany

Register to save articles to
your library

Register

Paper statistics

Downloads
54
Abstract Views
435
rank
370,495
PlumX Metrics