Learning Backward Induction: A Neural Network Agent Approach

Agent-Based Approaches in Economic and Social Complex Systems VI, edn. 2011, Springer, Japan, pp. 61 - 73, doi.org/10.1007/978-4-431-53907-0_5

Posted: 3 Oct 2005 Last revised: 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: September 12, 2009

Abstract

This paper addresses the question of whether neural networks (NNs), a realistic cognitive model of human information processing, can learn to backward induce in a two-stage game with a unique subgame-perfect Nash equilibrium. The NNs were found to predict the Nash equilibrium approximately 70% of the time in new games. Similarly to humans, the neural network agents are also found to suffer from subgame and truncation inconsistency, supporting the contention that they are appropriate models of general learning in humans. The agents were found to behave in a bounded rational manner as a result of the endogenous emergence of decision heuristics. In particular a very simple heuristic socialmax, that chooses the cell with the highest social payoff explains their behavior approximately 60% of the time, whereas the ownmax heuristic that simply chooses the cell with the maximum payoff for that agent fares worse explaining behavior roughly 38%, albeit still significantly better than chance. These two heuristics were found to be ecologically valid for the backward induction problem as they predicted the Nash equilibrium in 67% and 50% of the games respectively. Compared to various standard classification algorithms, the NNs were found to be only slightly more accurate than standard discriminant analyses. However, the latter do not model the dynamic learning process and have an ad hoc postulated functional form. In contrast, a NN agent’s behavior evolves with experience and is capable of taking on any functional form according to the universal approximation theorem.

Keywords: Agent based computational economics, Backward induction, Learning models, Behavioral game theory, Simulations, Complex adaptive systems, Artificial intelligence, Neural networks

JEL Classification: C73, C9, C45

Suggested Citation

Spiliopoulos, Leonidas, Learning Backward Induction: A Neural Network Agent Approach (September 12, 2009). Agent-Based Approaches in Economic and Social Complex Systems VI, edn. 2011, Springer, Japan, pp. 61 - 73, doi.org/10.1007/978-4-431-53907-0_5, Available at SSRN: https://ssrn.com/abstract=812044 or http://dx.doi.org/10.2139/ssrn.812044

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, 14195
Germany

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
185
Abstract Views
1,392
rank
224,367
PlumX Metrics