Humans versus computer algorithms in repeated mixed strategy games
This paper is concerned with the modeling of strategic change in humans’ behavior when facing diﬀerent types of opponents. In order to implement this eﬃciently a mixed experimental setup was used where subjects played a game with a unique mixed strategy Nash equilibrium for 100 rounds against 3 preprogrammed computer algorithms (CAs) designed to exploit diﬀerent modes of play. In this context, substituting human opponents with computer algorithms designed to exploit commonly occurring human behavior increases the experimental control of the researcher allowing for more powerful statistical tests. The results indicate that subjects signiﬁcantly change their behavior conditional on the type of CA opponent, exhibiting within-sub jects heterogeneity, but that there exists comparatively little between-subjects heterogeneity since players seemed to follow very similar strategies against each algorithm. Simple heuristics, such as win-stay/lose-shift, were found to model subjects and make out of sample predictions as well as, if not better than, more complicated models such as individually estimated EWA learning models which suﬀered from overﬁtting. Subjects modiﬁed their strategies in the direction of better response as calculated from CA simulations of various learning models, albeit not perfectly. Examples include the observation that subjects randomized more eﬀectively as the pattern recognition depth of the CAs increased, and the drastic reduction in the use of the win-stay/lose-shift heuristic when facing a CA designed to exploit this behavior.
|Date of creation:||09 Jan 2008|
|Date of revision:|
|Contact details of provider:|| Postal: |
Web page: http://mpra.ub.uni-muenchen.de
More information through EDIRC
References listed on IDEAS
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.:
- Peter Dürsch & Albert Kolb & Jörg Oechssler & Burkhard C. Schipper, 2005.
"Rage Against the Machines: How Subjects Learn to Play Against Computers,"
Bonn Econ Discussion Papers
bgse31_2005, University of Bonn, Germany.
- Peter Duersch & Albert Kolb & Joerg Oechssler & Burkhard Schipper, 2005. "Rage Against the Machines: How Subjects Learn to Play Against Computers," Game Theory and Information 0510012, EconWPA.
- Dürsch, Peter & Kolb, Albert & Oechssler, Jörg & Schipper, Burkhard C., 2005. "Rage Against the Machines: How Subjects Learn to Play Against Computers," Discussion Paper Series of SFB/TR 15 Governance and the Efficiency of Economic Systems 63, Free University of Berlin, Humboldt University of Berlin, University of Bonn, University of Mannheim, University of Munich.
- Burkhard C. Schipper & Jorg Oechssler & Albert Kolb, 2005. "Rage Against the Machines: How Subjects Learn to Play Against Computers," Working Papers 516, University of California, Davis, Department of Economics.
- Dürsch, Peter & Kolb, Albert & Oechssler, Jörg & Schipper, Burkhard, 2005. "Rage Against the Machines - How Subjects Learn to Play Against Computers," Sonderforschungsbereich 504 Publications 05-36, Sonderforschungsbereich 504, Universität Mannheim;Sonderforschungsbereich 504, University of Mannheim.
- Peter Dürsch & Albert Kolb & Jörg Oechssler & Burkhard C. Schipper, 2005. "Rage Against the Machines: How Subjects Learn to Play Against Computers," Working Papers 0423, University of Heidelberg, Department of Economics, revised Oct 2005.
- Jason Shachat & J. Todd Swarthout, 2002.
"Learning about Learning in Games through Experimental Control of Strategic Interdependence,"
Experimental Economics Center Working Paper Series
2006-17, Experimental Economics Center, Andrew Young School of Policy Studies, Georgia State University, revised Aug 2008.
- Shachat, Jason & Swarthout, J. Todd, 2012. "Learning about learning in games through experimental control of strategic interdependence," Journal of Economic Dynamics and Control, Elsevier, vol. 36(3), pages 383-402.
- Jason Shachat & J. Todd Swarthout, 2013. "Learning about learning in games through experimental control of strategic interdependence," Papers 2013-10-14, Working Paper.
- Jason Shachat & J. Todd Swarthout, 2003. "Learning about Learning in Games through Experimental Control of Strategic Interdependence," Experimental 0310003, EconWPA.
- Jason Shachat & J. Todd Swarthout, 2011. "Learning about learning in games through experimental control of strategic interdependence," Working Papers 1103, Xiamen Unversity, The Wang Yanan Institute for Studies in Economics, Finance and Economics Experimental Laboratory, revised 28 Apr 2011.
- Atanasios Mitropoulos, 2001. "On the Measurement of the Predictive Success of Learning Theories in Repeated Games," Experimental 0110001, EconWPA.
- Jason Shachat & J. Todd Swarthout, 2003.
"Do We Detect and Exploit Mixed Strategy Play by Opponents?,"
- Jason Shachat & J. Todd Swarthout, 2004. "Do we detect and exploit mixed strategy play by opponents?," Mathematical Methods of Operations Research, Springer, vol. 59(3), pages 359-373, 07.
- Bonetti, Shane, 1998. "Experimental economics and deception," Journal of Economic Psychology, Elsevier, vol. 19(3), pages 377-395, June.
- Harrison, Glenn W, 1989. "Theory and Misbehavior of First-Price Auctions," American Economic Review, American Economic Association, vol. 79(4), pages 749-62, September.
- Smith, Vernon L & Walker, James M, 1993. "Rewards, Experience and Decision Costs in First Price Auctions," Economic Inquiry, Western Economic Association International, vol. 31(2), pages 237-45, April.
- Spiliopoulos, Leonidas, 2008. "Do repeated game players detect patterns in opponents? Revisiting the Nyarko & Schotter belief elicitation experiment," MPRA Paper 6666, University Library of Munich, Germany.
- Walker, James M. & Smith, Vernon L. & Cox, James C., 1987. "Bidding behavior in first price sealed bid auctions : Use of computerized Nash competitors," Economics Letters, Elsevier, vol. 23(3), pages 239-244.
- Colin Camerer & Teck-Hua Ho, 1999. "Experience-weighted Attraction Learning in Normal Form Games," Econometrica, Econometric Society, vol. 67(4), pages 827-874, July.
- Yaw Nyarko & Andrew Schotter, 2002. "An Experimental Study of Belief Learning Using Elicited Beliefs," Econometrica, Econometric Society, vol. 70(3), pages 971-1005, May.
- repec:spr:compst:v:59:y:2004:i:3:p:359-373 is not listed on IDEAS
- White, Halbert, 1980. "A Heteroskedasticity-Consistent Covariance Matrix Estimator and a Direct Test for Heteroskedasticity," Econometrica, Econometric Society, vol. 48(4), pages 817-38, May.
When requesting a correction, please mention this item's handle: RePEc:pra:mprapa:6672. 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: (Ekkehart Schlicht)
If references are entirely missing, you can add them using this form.