Robust Learning for Repeated Stochastic Games via Meta-Gaming

Abstract

In repeated stochastic games (RSGs), an agent must quickly adapt to the behavior of previously unknown associates, who may themselves be learning. This machine-learning problem is particularly challenging due, in part, to the presence of multiple (even infinite) equilibria and inherently large strategy spaces. In this paper, we introduce a method to reduce… (More)

Topics

8 Figures and Tables

Cite this paper

@inproceedings{Crandall2015RobustLF, title={Robust Learning for Repeated Stochastic Games via Meta-Gaming}, author={Jacob W. Crandall}, booktitle={IJCAI}, year={2015} }