Can the human mind learn to backward induce? A neural network answer.

This paper addresses the question of whether neural networks, a realistic cognitive model of the human information processing, can learn to backward induce in a two stage game with a unique subgame-perfect Nash Equilibrium. The result that the neural networks only learn a heuristic that approximates the desired output and does not backward induce is in accordance with the documented difficulty of humans to apply backward induction and their dependence on heuristics.

MoreLess

Year of publication:	2005-05-30
Authors:	Spiliopoulos, Leonidas
Institutions:	EconWPA
Subject:	behavioral game theory \| neural networks \| learning

More details

Extent:	application/pdf
Series:	Game Theory and Information.
Type of publication:	Book / Working Paper
Notes:	Type of Document - pdf; pages: 9 9 pages
Classification:	C7 - Game Theory and Bargaining Theory ; D8 - Information and Uncertainty
Source:	RePEc - Research Papers in Economics

Persistent link: https://www.econbiz.de/10005062328