IDEAS home Printed from https://ideas.repec.org/p/pri/metric/wp001_2011.pdf.html
   My bibliography  Save this paper

Endogenous Learning with Bounded Memory

Author

Listed:
  • Yilmaz Kocer

    (Princeton University)

Abstract

I analyze the effects of memory limitations on the endogenous learning behavior of an agent in a standard two-armed bandit problem. An infinitely lived agent chooses each period between two alternatives with unknown types, to maximize discounted payoffs. The agent can experiment with each alternative and receive payoffs that are partially informative about its type. The agent does not recall past actions or payoffs. Instead, the agent has a finite number of memory states as in Wilson (2004): he can condition his actions only on the memory state he is currently in, and he can update his memory state depending on the payoff received. I find that the inclination to choose the currently better alternative does not con- strain learning in the limit as discounting vanishes. Even though uncertainties are independent, the agent optimally holds correlated beliefs across memory states. Optimally, memory states reflect the magnitude of the relative ranking of alternatives. After a high payoff from one of the alternatives, the agent optimally moves to a memory state with more pessimistic beliefs on the other, even though no information about the latter alternative is received. For the case where one alternative is substantially more informative than the other, he chooses the latter only for myopic exploitation purposes, and ignores any information about it, suggesting specialization in learning. For the special case with one known (safe) alternative, a sufficiently patient agent never ceases experimentation and tries the unknown alternative at least occasionally after any history. Furthermore, he chooses the safe alternative with more optimistic beliefs than the optimal full memory cutoff belief, suggesting under-experimentation. Both are counter to what theory predicts with full memory, but in agreement with experimental findings.

Suggested Citation

  • Yilmaz Kocer, 2010. "Endogenous Learning with Bounded Memory," Working Papers 1290, Princeton University, Department of Economics, Econometric Research Program..
  • Handle: RePEc:pri:metric:wp001_2011.pdf
    as

    Download full text from publisher

    File URL: http://detc.princeton.edu/wp-content/uploads/2016/11/wp001_2011.pdf
    Download Restriction: no

    References listed on IDEAS

    as
    1. Huck Steffen & Sarin Rajiv, 2004. "Players With Limited Memory," The B.E. Journal of Theoretical Economics, De Gruyter, vol. 4(1), pages 1-27, September.
    2. Kalai, Ehud & Solan, Eilon, 2003. "Randomization and simplification in dynamic decision-making," Journal of Economic Theory, Elsevier, vol. 111(2), pages 251-264, August.
    3. Bruno Frey, 2005. "‘‘Just forget it.’’ Memory distortions as bounded rationality," Mind & Society: Cognitive Studies in Economics and Social Sciences, Springer;Fondazione Rosselli, vol. 4(1), pages 13-25, June.
    4. Piccione, Michele & Rubinstein, Ariel, 1997. "The Absent-Minded Driver's Paradox: Synthesis and Responses," Games and Economic Behavior, Elsevier, vol. 20(1), pages 121-130, July.
    5. Jeffrey Banks & David Porter & Mark Olson, 1997. "An experimental analysis of the bandit problem," Economic Theory, Springer;Society for the Advancement of Economic Theory (SAET), vol. 10(1), pages 55-77.
    6. Banks, Jeffrey S. & Sundaram, Rangarajan K., 1990. "Repeated games, finite automata, and complexity," Games and Economic Behavior, Elsevier, vol. 2(2), pages 97-117, June.
    7. James Dow, 1991. "Search Decisions with Limited Memory," Review of Economic Studies, Oxford University Press, vol. 58(1), pages 1-14.
    8. Peng, Lin, 2005. "Learning with Information Capacity Constraints," Journal of Financial and Quantitative Analysis, Cambridge University Press, vol. 40(2), pages 307-329, June.
    9. Nitin Mehta & Surendra Rajiv & Kannan Srinivasan, 2004. "Role of Forgetting in Memory-Based Choice Decisions: A Structural Model," Quantitative Marketing and Economics (QME), Springer, vol. 2(2), pages 107-140, June.
    10. Piccione, Michele & Rubinstein, Ariel, 1997. "On the Interpretation of Decision Problems with Imperfect Recall," Games and Economic Behavior, Elsevier, vol. 20(1), pages 3-24, July.
    11. Noah Gans & George Knox & Rachel Croson, 2007. "Simple Models of Discrete Choice and Their Performance in Bandit Experiments," Manufacturing & Service Operations Management, INFORMS, vol. 9(4), pages 383-408, December.
    12. Matthew Rabin, 1998. "Psychology and Economics," Journal of Economic Literature, American Economic Association, vol. 36(1), pages 11-46, March.
    13. Kandori, Michihiro & Mailath, George J & Rob, Rafael, 1993. "Learning, Mutation, and Long Run Equilibria in Games," Econometrica, Econometric Society, vol. 61(1), pages 29-56, January.
    14. Drew Fudenberg & David K. Levine, 1998. "The Theory of Learning in Games," MIT Press Books, The MIT Press, edition 1, volume 1, number 0262061945.
    15. Theodoros M. Diasakos, 2008. "Complexity and Bounded Rationality in Individual Decision Problems," Carlo Alberto Notebooks 90, Collegio Carlo Alberto.
    16. Peng, Lin & Xiong, Wei, 2006. "Investor attention, overconfidence and category learning," Journal of Financial Economics, Elsevier, vol. 80(3), pages 563-602, June.
    17. Tülin Erdem & Kannan Srinivasan & Wilfred Amaldoss & Patrick Bajari & Hai Che & Teck Ho & Wes Hutchinson & Michael Katz & Michael Keane & Robert Meyer & Peter Reiss, 2005. "Theory-Driven Choice Models," Marketing Letters, Springer, vol. 16(3), pages 225-237, December.
    18. B. Douglas Bernheim & Raphael Thomadsen, 2005. "Memory and Anticipation," Economic Journal, Royal Economic Society, vol. 115(503), pages 271-304, April.
    19. Barton L. Lipman, 1995. "Information Processing and Bounded Rationality: A Survey," Canadian Journal of Economics, Canadian Economics Association, vol. 28(1), pages 42-67, February.
    20. Gerd Gigerenzer & Reinhard Selten (ed.), 2002. "Bounded Rationality: The Adaptive Toolbox," MIT Press Books, The MIT Press, edition 1, volume 1, number 0262571641.
    21. Winter, Sidney G., 1982. "Binary choice and the supply of memory," Journal of Economic Behavior & Organization, Elsevier, vol. 3(4), pages 277-321, December.
    22. Robert J. Meyer & Yong Shi, 1995. "Sequential Choice Under Ambiguity: Intuitive Solutions to the Armed-Bandit Problem," Management Science, INFORMS, vol. 41(5), pages 817-834, May.
    23. Antonio G. Chessa & Jaap M. J. Murre, 2007. "A Neurocognitive Model of Advertisement Content and Brand Name Recall," Marketing Science, INFORMS, vol. 26(1), pages 130-141, 01-02.
    24. Aumann, Robert J. & Hart, Sergiu & Perry, Motty, 1997. "The Absent-Minded Driver," Games and Economic Behavior, Elsevier, vol. 20(1), pages 102-116, July.
    25. Eliaz, Kfir, 2003. "Nash equilibrium when players account for the complexity of their forecasts," Games and Economic Behavior, Elsevier, vol. 44(2), pages 286-310, August.
    26. MacLeod W. Bentley, 2002. "Complexity, Bounded Rationality and Heuristic Search," The B.E. Journal of Economic Analysis & Policy, De Gruyter, vol. 1(1), pages 1-52, September.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Daniel Monte & Maher Said, 2014. "The value of (bounded) memory in a changing world," Economic Theory, Springer;Society for the Advancement of Economic Theory (SAET), vol. 56(1), pages 59-82, May.
    2. Alejandro Núñez Arroyo, 2018. "Information seeking with selective memory," Documentos CEDE 017131, Universidad de los Andes - CEDE.
    3. Alessandro Pavan, 2014. "Attention, Coordination, and Bounded Recall," Discussion Papers 1576, Northwestern University, Center for Mathematical Studies in Economics and Management Science.
    4. Nicholas Janetos, 2017. "Fads and imperfect information," PIER Working Paper Archive 17-009, Penn Institute for Economic Research, Department of Economics, University of Pennsylvania, revised 01 May 2017.

    More about this item

    Keywords

    endogenous learning behavior; memory limitations; two-armed bandit problem;

    JEL classification:

    • C01 - Mathematical and Quantitative Methods - - General - - - Econometrics
    • D01 - Microeconomics - - General - - - Microeconomic Behavior: Underlying Principles
    • D11 - Microeconomics - - Household Behavior - - - Consumer Economics: Theory
    • H31 - Public Economics - - Fiscal Policies and Behavior of Economic Agents - - - Household

    Statistics

    Access and download statistics

    Corrections

    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:pri:metric:wp001_2011.pdf. 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: (Bobray Bordelon). General contact details of provider: http://edirc.repec.org/data/exprius.html .

    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.

    If CitEc recognized a reference but did not link an item in RePEc to it, you can help with 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.