Strategy Learning in 3x3 Games by Neural Networks

Daniel Sgroi and Daniel John Zizzo

Cambridge Working Papers in Economics from Faculty of Economics, University of Cambridge

Abstract: This paper presents a neural network based methodology for examining the learning of game-playing rules in never-before seen games. A network is trained to pick Nash equilibria in a set of games and then released to play a larger set of new games. While faultlessly selecting Nash equilibria in never-before seen games is too complex a task for the network, Nash equilibria are chosen approximately 60% of the times. Furthermore, despite training the network to select Nash equilibria, what emerges are endogenously obtained bounded-rational rules which are closer to payoff dominance, and the best response to payoff dominance.

Keywords: rationality; learning; neural networks; normal form games; complexity (search for similar items in EconPapers)
JEL-codes: C72 D00 D83 (search for similar items in EconPapers)
New Economics Papers: this item is included in nep-cmp and nep-mic
Date: 2002-03
Note: EMT
View list of references View citations in EconPapers

Downloads: (external link)
http://www.econ.cam.ac.uk/dae/repec/cam/pdf/wp0207.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: http://EconPapers.repec.org/RePEc:cam:camdae:0207

Access Statistics for this paper

More papers in Cambridge Working Papers in Economics from Faculty of Economics, University of Cambridge
Series data maintained by Howard Cobb ().