Skip to main content
SpringerLink
Log in

On the Role of the Group Composition for Achieving Optimality

  • Published:
Annals of Operations Research Aims and scope Submit manuscript

Abstract

We show the inability of any pure strategy imitation rule for leading a decision maker towards optimality for given and fixed population behaviour. The intuition is that a pure strategy state space is too small to deal with a large variety of environments. This result helps to understand the optimality result obtained by Schlag (1998), where the population behaviour is let to evolve over time. The intuition is that the group composition provides an additional state space in which information about the environment can be accumulated.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  • Binmore, K. (1987). “Modeling Rational Players, I andII.” Economics and Philosophy 3, 179–214.

    Google Scholar 

  • Binmore, K. (1987). “Modeling Rational Players, I andII.” Economics and Philosophy 4, 9–55.

    Article  Google Scholar 

  • Börgers, T. and R. Sarin. (1997). “LearningThrough Reinforcement and Replicator Dynamics.” Journal of EconomicTheory 77, 1–14.

    Google Scholar 

  • Börgers, T., A.J. Morales, and R. Sarin.(1998). “Simple Behaviour Rules Which Lead To Expected Payoff MaximisingChoices.” mimeo UCL.

  • Cross, J. (1973). “A Stochastic Learning Model ofEconomic behaviour.” Quarterly Journal of Economics 87, 239–266.

    Article  Google Scholar 

  • Erev, I., and A. Roth. (1998). “Predicting HowPeople Play Games: Reinforcement Learning in Experimental Games with Unique,Mixed Strategy Equilibria.” American Economic Review 88, 848–881.

    Google Scholar 

  • Fudenberg, D. and D. Levine. (1998). The Theoryof Learning in Games. Cambridge: MIT Press.

    Google Scholar 

  • Grimmett, G. and D. Stirzaker. (1992). Probability and Random Processes (2nd edition). Oxford: Clarendon Press.

    Google Scholar 

  • Hopkins, Ed. (2002). “Two Competing Models of How PeopleLearn in Games.” Econometrica 70, 2141–2166.

    Article  Google Scholar 

  • Hopkins, Ed and M. Posch. (2002). “Attainability of Boundary Points under Reinforcement Learning.” forthcomingin Games and Economic Behaviour.

  • Karandikar, R., D. Mookherjee, D. Ray, and F. Vega-Redondo. (1998). “Evolving Aspirations and Cooperation.” Journal of Economic Theory 80, 292–331.

    Article  Google Scholar 

  • Roth, A. and I. Erev. (1995). “Learning inExtensive-Form Games: Experimental Data and Simple Dynamic Models in theIntermediate Term.” Games and Economic Behavior 8, 164–212.

    Article  Google Scholar 

  • Rustichini, A. (1999). “Optimal Properties ofStimulus-Response Learning Models.” Games and Economic Behavior 29, 244–273.

    Article  Google Scholar 

  • Schlag, K. (1998). “Why Imitate, and if so, How? ABoundedly Rational Approach to Multi-armed Bandits.” Journalof Economic Theory 78, 130–156.

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Departamento de Teoría e Historia Económica, Facultad de Ciencias Económicas, University of Malaga, Plaza El Ejido s/n, 29013, Malaga, Spain

    Antonio J. Morales

Authors
  1. Antonio J. Morales
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Antonio J. Morales.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Morales, A.J. On the Role of the Group Composition for Achieving Optimality. Ann Oper Res 137, 387–397 (2005). https://doi.org/10.1007/s10479-005-2268-1

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10479-005-2268-1

Keywords

Search

Navigation