Abstract
We present a novel deep convolutional neural network (DCNN) model for predicting human behavior in repeated games. The model is the first deep neural network presented on repeated games that is able to be trained on games with arbitrary size of payoff matrices. Our neural network takes the players’ payoff matrices and the history of the play as input, and outputs the predicted action picked by the first player in the next round. To evaluate the model’s performance, we apply it to some experimental games played by humans and measure the rate of correctly predicted actions. The results show that our model obtains an average prediction accuracy of about 63% across all the studied games, which is about 6% higher than the best average accuracy obtained by the baseline models in the literature.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Camerer, C.F., Ho, T.H.: Behavioral game theory experiments and modeling (chapter 10). In: Handbook of Game Theory with Economic Applications (Vol. 4, pp. 517–573). Elsevier (2015).
Chen, W., Chen, Y., Levine, D.K.: A unifying learning framework for building artificial game-playing agents. Ann. Math. Artif. Intell. 73(3–4), 335–358 (2015)
Fudenberg, D., Levine, D.K.: Whither game theory? Towards a theory of learning in games. VOPROSY ECONOMIK I, 5 (2017)
Fudenberg, D., Liang, A.: Predicting and understanding initial play. Am. Econ. Rev. 109(12), 4112–4141 (2019)
Hyndman, K., Ozbay, E.Y., Schotter, A., Ehrblatt, W.Z.E.: Convergence: an experimental study of teaching and learning in repeated games. J. Eur. Econ. Assoc. 10(3), 573–604 (2012)
Izquierdo, L.R., Izquierdo, S.S., & Vega-Redondo, F.: Learning and evolutionary game theory. In: Encyclopedia of the Sciences of Learning. Springer, Boston (2012)
Mengel, F.: Learning by (limited) forward looking players. J. Econ. Behav. Organ. 108, 59–77 (2014)
Kolumbus, Y., Noti, G.: Neural networks for predicting human interactions in repeated games. arXiv preprint arXiv:1911.03233 (2019).
Mathevet, L., & Romero, J. (2012). Predictive repeated game theory: Measures and experiments.
Cason, T.N., Lau, S.H.P., Mui, V.L.: Learning, teaching, and turn taking in the repeated assignment game. Econ. Theor. 54(2), 335–357 (2013)
Camerer, C.F., Ho, T.H.: Experience-weighted attraction learning in normal form games. Econometrica 67(4), 827–874 (1999)
Camerer, C., Ho, T., Chong, K.: Models of thinking, learning, and teaching in games. Am. Econ. Rev. 93(2), 192–195 (2003)
Bhatia, S., Golman, R.: A recurrent neural network for game theoretic decision making. In: Proceedings of the Annual Meeting of the Cognitive Science Society (Vol. 36, No. 36) (2014).
Hartford, J.S., Wright, J.R., Leyton-Brown, K.: Deep learning for predicting human strategic behavior. In: Advances in Neural Information Processing Systems (2016).
Erev, I., Roth, A.E.: Predicting how people play games: reinforcement learning in experimental games with unique, mixed strategy equilibria. Am. Econ. Rev. 848–881 (1998).
Brown, G.W.: Iterative solution of games by fictitious play. Act. Anal. Prod. Allocat. 13(1), 374–376 (1951)
Elie, R., Pérolat, J., Laurière, M., Geist, M., Pietquin, O.: Approximate fictitious play for mean field games. arXiv preprint arXiv:1907.02633 (2019).
Kamra, N., Gupta, U., Wang, K., Fang, F., Liu, Y., Tambe, M.: Deep fictitious play for games with continuous action spaces. In: Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems (pp. 2042–2044). International Foundation for Autonomous Agents and Multiagent Systems (2019).
Lanctot, M., Lockhart, E., Lespiau, J.B., Zambaldi, V., Upadhyay, S., Pérolat, J., et al.: Openspiel: a framework for reinforcement learning in games. arXiv preprint arXiv:1908.09453.
Ma, W.C., Huang, D.A., Lee, N., Kitani, K.M.: Forecasting interactive dynamics of pedestrians with fictitious play. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 774–782) (2017).
Wang, H., Yu, C., Wu, L.: A neighborhood correlated empirical weighted algorithm for fictitious play. In: Life System Modeling and Intelligent Computing (pp. 305–311). Springer, Berlin (2010)
Ansari, A., Montoya, R., Netzer, O.: Dynamic learning in behavioral games: a hidden Markov mixture-of-experts approach. Quant. Mark. Econ. 10(4), 475–503 (2012)
Ho, T.H., Camerer, C.F., Chong, J.K.: Self-tuning experience weighted attraction learning in games. J. Econ. Theory 133(1), 177–198 (2007)
Hart, S., Mas-Colell, A.: A simple adaptive procedure leading to correlated equilibrium. Econometrica 68(5), 1127–1150 (2000)
McKelvey, R.D., Palfrey, T.R.: Quantal response equilibria for normal form games. Games Econom. Behav. 10(1), 6–38 (1995)
Camerer, C.F., Ho, T.H., Chong, J.K.: A cognitive hierarchy model of games. Q. J. Econ. 119(3), 861–898 (2004)
Selten, R., Chmura, T.: Stationary concepts for experimental 2x2-games. Am. Econ. Rev. 98(3), 938–966 (2008)
Mookherjee, D., Sopher, B.: Learning and decision costs in experimental constant sum games. Games Econom. Behav. 19(1), 97–132 (1997)
Rapoport, A., Amaldoss, W.: Mixed strategies and iterative elimination of strongly dominated strategies: an experimental investigation of states of knowledge. J. Econ. Behav. Organ. 42(4), 483–521 (2000)
Van Huyck, J.B., Battalio, R.C., Beil, R.O.: Tacit coordination games, strategic uncertainty, and coordination failure. Am. Econ. Rev. 80(1), 234–248 (1990)
Andreoni, J., Miller, J.H.: Rational cooperation in the finitely repeated prisoner’s dilemma: experimental evidence. Econ. J. 103(418), 570–585 (1993)
Marchiori, D., Warglien, M.: Predicting human interactive learning by regret-driven neural networks. Science 319(5866), 1111–1113 (2008)
Author information
Authors and Affiliations
Corresponding authors
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendices
Appendix 1
This appendix is dedicated to the payoff matrices of the behavioral games used in our experiments.
Appendix 2
This appendix is dedicated to the learning curves of training the proposed network on the behavioral games in Table 2. The curves demonstrate loss and accuracy of the network obtained in 60 epochs of one training phase on the whole train set, reported individually for each game. However, in the Results section of the paper, the test results are reported based on the network trained for 6 times on the train set, each consisting of one epoch on every subject.
Rights and permissions
About this article
Cite this article
Vazifedan, A., Izadi, M. Predicting human behavior in size-variant repeated games through deep convolutional neural networks. Prog Artif Intell 11, 15–28 (2022). https://doi.org/10.1007/s13748-021-00258-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13748-021-00258-y