Learning Game Representations from Data Using Rationality Constraints

Xi Alice Gao, Avi Pfeffer
Proceedings of the 26th Conference on Uncertainty in Artificial Intelligence, PMLR R8:201-208, 2010.

Abstract

While game theory is widely used to model strategic interactions, a natural question is where do the game representations come from? One answer is to learn the representations from data. If one wants to learn both the payoffs and the players’ strategies, a naive approach is to learn them both directly from the data. This approach ignores the fact the players might be playing reasonably good strategies, so there is a connection between the strategies and the data. The main contribution of this paper is to make this connection while learning. We formulate the learning problem as a weighted constraint satisfaction problem, including constraints both for the fit of the payoffs and strategies to the data and the fit of the strategies to the payoffs. We use quantal response equilibrium as our notion of rationality for quantifying the latter fit. Our results show that incorporating rationality constraints can improve learning when the amount of data is limited.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR8-gao10a, title = {Learning Game Representations from Data Using Rationality Constraints}, author = {Gao, Xi Alice and Pfeffer, Avi}, booktitle = {Proceedings of the 26th Conference on Uncertainty in Artificial Intelligence}, pages = {201--208}, year = {2010}, editor = {Grünwald, Peter and Spirtes, Peter}, volume = {R8}, series = {Proceedings of Machine Learning Research}, month = {08--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r8/main/assets/gao10a/gao10a.pdf}, url = {https://proceedings.mlr.press/r8/gao10a.html}, abstract = {While game theory is widely used to model strategic interactions, a natural question is where do the game representations come from? One answer is to learn the representations from data. If one wants to learn both the payoffs and the players’ strategies, a naive approach is to learn them both directly from the data. This approach ignores the fact the players might be playing reasonably good strategies, so there is a connection between the strategies and the data. The main contribution of this paper is to make this connection while learning. We formulate the learning problem as a weighted constraint satisfaction problem, including constraints both for the fit of the payoffs and strategies to the data and the fit of the strategies to the payoffs. We use quantal response equilibrium as our notion of rationality for quantifying the latter fit. Our results show that incorporating rationality constraints can improve learning when the amount of data is limited.}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T Learning Game Representations from Data Using Rationality Constraints %A Xi Alice Gao %A Avi Pfeffer %B Proceedings of the 26th Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2010 %E Peter Grünwald %E Peter Spirtes %F pmlr-vR8-gao10a %I PMLR %P 201--208 %U https://proceedings.mlr.press/r8/gao10a.html %V R8 %X While game theory is widely used to model strategic interactions, a natural question is where do the game representations come from? One answer is to learn the representations from data. If one wants to learn both the payoffs and the players’ strategies, a naive approach is to learn them both directly from the data. This approach ignores the fact the players might be playing reasonably good strategies, so there is a connection between the strategies and the data. The main contribution of this paper is to make this connection while learning. We formulate the learning problem as a weighted constraint satisfaction problem, including constraints both for the fit of the payoffs and strategies to the data and the fit of the strategies to the payoffs. We use quantal response equilibrium as our notion of rationality for quantifying the latter fit. Our results show that incorporating rationality constraints can improve learning when the amount of data is limited. %Z Reissued by PMLR on 04 October 2026.
APA
Gao, X.A. & Pfeffer, A.. (2010). Learning Game Representations from Data Using Rationality Constraints. Proceedings of the 26th Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R8:201-208 Available from https://proceedings.mlr.press/r8/gao10a.html. Reissued by PMLR on 04 October 2026.

Related Material