IDEAS home Printed from
   My bibliography  Save this paper

Learning backward induction: a neural network agent approach


  • Leonidas, Spiliopoulos


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.

Suggested Citation

  • Leonidas, Spiliopoulos, 2009. "Learning backward induction: a neural network agent approach," MPRA Paper 17267, University Library of Munich, Germany.
  • Handle: RePEc:pra:mprapa:17267

    Download full text from publisher

    File URL:
    File Function: original version
    Download Restriction: no

    File URL:
    File Function: revised version
    Download Restriction: no

    References listed on IDEAS

    1. Ivohasina Fizara Razafimahefa & Shigeyuki Hamori, 2005. "Import Demand Function: Some Evidence from Madagascar and Mauritius," Journal of African Economies, Centre for the Study of African Economies (CSAE), vol. 14(3), pages 411-434, September.
    2. repec:spr:adstae:978-3-540-68921-8 is not listed on IDEAS
    3. Urbain, Jean-Pierre, 1996. "Japanese import behavior and cointegration: A comment," Journal of Policy Modeling, Elsevier, vol. 18(6), pages 583-601, December.
    4. Carone, Giuseppe, 1996. "Modeling the U.S. demand for imports through cointegration and error correction," Journal of Policy Modeling, Elsevier, vol. 18(1), pages 1-48, February.
    5. Pedroni, Peter, 2004. "Panel Cointegration: Asymptotic And Finite Sample Properties Of Pooled Time Series Tests With An Application To The Ppp Hypothesis," Econometric Theory, Cambridge University Press, vol. 20(03), pages 597-625, June.
    6. Nasri Harb, 2005. "Import demand in heterogeneous panel setting," Applied Economics, Taylor & Francis Journals, vol. 37(20), pages 2407-2415.
    7. Johansen, Soren & Juselius, Katarina, 1990. "Maximum Likelihood Estimation and Inference on Cointegration--With Applications to the Demand for Money," Oxford Bulletin of Economics and Statistics, Department of Economics, University of Oxford, vol. 52(2), pages 169-210, May.
    8. Dilip Dutta & Nasiruddin Ahmed, 2004. "An aggregate import demand function for India: a cointegration analysis," Applied Economics Letters, Taylor & Francis Journals, vol. 11(10), pages 607-613.
    9. Mohsin S. Khan, 1974. "Import and Export Demand in Developing Countries (Demande à l'importation et l'exportation dans les pays en développement) (La demanda de importación y de exportación en los países en desarrollo)," IMF Staff Papers, Palgrave Macmillan, vol. 21(3), pages 678-693, November.
    10. Hamori, Shigeyuki & Matsubayashi, Yoichi, 2001. "An empirical analysis on the stability of Japan's aggregate import demand function," Japan and the World Economy, Elsevier, vol. 13(2), pages 135-144, April.
    11. Kao, Chihwa, 1999. "Spurious regression and residual-based tests for cointegration in panel data," Journal of Econometrics, Elsevier, vol. 90(1), pages 1-44, May.
    12. Peter Pedroni, 2000. "Fully Modified OLS for Heterogeneous Cointegrated Panels," Department of Economics Working Papers 2000-03, Department of Economics, Williams College.
    13. Carmen M. Reinhart, 1995. "Devaluation, Relative Prices, and International Trade: Evidence from Developing Countries," IMF Staff Papers, Palgrave Macmillan, vol. 42(2), pages 290-312, June.
    14. Im, Kyung So & Pesaran, M. Hashem & Shin, Yongcheol, 2003. "Testing for unit roots in heterogeneous panels," Journal of Econometrics, Elsevier, vol. 115(1), pages 53-74, July.
    15. Sawyer, W. Charles & Sprinkle, Richard L., 1997. "The Demand for Imports and Exports in Japan: A Survey," Journal of the Japanese and International Economies, Elsevier, vol. 11(2), pages 247-259, June.
    16. Pedroni, Peter, 1999. " Critical Values for Cointegration Tests in Heterogeneous Panels with Multiple Regressors," Oxford Bulletin of Economics and Statistics, Department of Economics, University of Oxford, vol. 61(0), pages 653-670, Special I.
    17. Maddala, G S & Wu, Shaowen, 1999. " A Comparative Study of Unit Root Tests with Panel Data and a New Simple Test," Oxford Bulletin of Economics and Statistics, Department of Economics, University of Oxford, vol. 61(0), pages 631-652, Special I.
    18. Bahmani-Oskooee, Mohsen & Ratha, Artatrana, 2008. "Exchange rate sensitivity of US bilateral trade flows," Economic Systems, Elsevier, vol. 32(2), pages 129-141, June.
    19. Urbain, J-P., 1988. "Error Correction Models For Aggregate Imports: The Case Of Two Small Open European Economies," Papers 8804, Liege - Centre de Recherches Economiques et Demographiques.
    20. Mah, Jai Sheen, 1994. "Japanese import demand behavior: The cointegration approach," Journal of Policy Modeling, Elsevier, vol. 16(3), pages 291-298, June.
    21. Choi, In, 2001. "Unit root tests for panel data," Journal of International Money and Finance, Elsevier, vol. 20(2), pages 249-272, April.
    22. Goldstein, Morris & Khan, Mohsin S., 1985. "Income and price effects in foreign trade," Handbook of International Economics,in: R. W. Jones & P. B. Kenen (ed.), Handbook of International Economics, edition 1, volume 2, chapter 20, pages 1041-1105 Elsevier.
    23. Masih, Rumi & Masih, Abul M. M., 2000. "A Reassessment of Long-Run Elasticities of Japanese Import Demand," Journal of Policy Modeling, Elsevier, vol. 22(5), pages 625-639, September.
    24. Dilip Dutta & Nasiruddin Ahmed, 1999. "An aggregate import demand function for Bangladesh: a cointegration approach," Applied Economics, Taylor & Francis Journals, vol. 31(4), pages 465-472.
    25. Yoichi Matsubayashi & Shigeyuki Hamori, 2003. "Some international evidence on the stability of aggregate import demand function," Applied Economics, Taylor & Francis Journals, vol. 35(13), pages 1497-1504.
    26. Faini, Riccardo & Pritchett, Lant & Clavijo, Fernando, 1988. "Import demand in developing countries," Policy Research Working Paper Series 122, The World Bank.
    27. Reinhart, Carmen, 1994. "Devaluation, Relative Prices, and International Trade," MPRA Paper 13708, University Library of Munich, Germany.
    28. Levin, Andrew & Lin, Chien-Fu & James Chu, Chia-Shang, 2002. "Unit root tests in panel data: asymptotic and finite-sample properties," Journal of Econometrics, Elsevier, vol. 108(1), pages 1-24, May.
    29. Peter Pedroni, 2001. "Purchasing Power Parity Tests In Cointegrated Panels," The Review of Economics and Statistics, MIT Press, vol. 83(4), pages 727-731, November.
    Full references (including those not matched with items on IDEAS)

    More about this item


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

    JEL classification:

    • C45 - Mathematical and Quantitative Methods - - Econometric and Statistical Methods: Special Topics - - - Neural Networks and Related Topics
    • C7 - Mathematical and Quantitative Methods - - Game Theory and Bargaining Theory
    • C73 - Mathematical and Quantitative Methods - - Game Theory and Bargaining Theory - - - Stochastic and Dynamic Games; Evolutionary Games

    NEP fields

    This paper has been announced in the following NEP Reports:


    Access and download statistics


    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:pra:mprapa:17267. 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: (Joachim Winter) or (Rebekah McClure). General contact details of provider: .

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    We have no references for this item. You can help adding them by using this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service hosted by the Research Division of the Federal Reserve Bank of St. Louis . RePEc uses bibliographic data supplied by the respective publishers.