Regret Circuits: Composability of Regret Minimizers

Gabriele Farina, Christian Kroer and Tuomas Sandholm


Regret minimization is a powerful tool for solving large-scale problems; it was recently used in breakthrough results for large-scale extensive-form game solving. This was achieved by composing simplex regret minimizers into an overall regret-minimization framework for extensive-form game strategy spaces. In this paper we study the general composability of regret minimizers. We derive a calculus for constructing regret minimizers for composite convex sets that are obtained from convexity-preserving operations on simpler convex sets. We show that local regret minimizers for the simpler sets can be combined with additional regret minimizers into an aggregate regret minimizer for the composite set. As one application, we show that the CFR framework can be constructed easily from our framework. We also show ways to include curtailing (constraining) operations into our framework. For one, they enable the construction of CFR generalization for extensive-form games with general convex strategy constraints that can cut across decision points.

Bibtex entry

@inproceedings{Farina19:Regret, title={Regret Circuits: Composability of Regret Minimizers}, author={Farina, Gabriele and Kroer, Christian and Sandholm, Tuomas}, booktitle={International Conference on Machine Learning}, year={2019} }