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.
Please report citation or reference errors to , or , if you are the registered author of the cited work, log in to your RePEc Author Service profile, click on "citations" and make appropriate adjustments.:
- John C. Harsanyi & Reinhard Selten, 1988. "A General Theory of Equilibrium Selection in Games," MIT Press Books, The MIT Press, edition 1, volume 1, number 0262582384, July.
- Binmore, Ken & McCarthy, John & Ponti, Giovanni & Samuelson, Larry & Shaked, Avner, 2002.
"A Backward Induction Experiment,"
Journal of Economic Theory,
Elsevier, vol. 104(1), pages 48-88, May.
- Binmore,K. & McCarthy,J. & Ponti,G. & ..., 1999. "A backward induction experiment," Working papers 34, Wisconsin Madison - Social Systems.
- Nakamura, Emi, 2005. "Inflation forecasting using a neural network," Economics Letters, Elsevier, vol. 86(3), pages 373-378, March.
- D. Sgroi & D. J. Zizzo, 2002. "Strategy Learning in 3x3 Games by Neural Networks," Cambridge Working Papers in Economics 0207, Faculty of Economics, University of Cambridge. Full references (including those not matched with items on IDEAS)
When requesting a correction, please mention this item's handle: RePEc:wpa:wuwpga:0505008. See general information about how to correct material in RePEc.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (EconWPA)
If references are entirely missing, you can add them using this form.