Regret Circuits: Composability of Regret Minimizers

Abstract

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 enables the construction of CFR generalization for extensive-form games with general convex strategy constraints that can cut across decision points.

Cited by in corpus (8)

• Near-Optimal No-Regret Learning for Correlated Equilibria in Multi-Player General-Sum Games
• Polynomial-Time Computation of Optimal Correlated Equilibria in Two-Player Extensive-Form Games with Public Chance Moves and Beyond
• Stochastic Regret Minimization in Extensive-Form Games
• Bounds for Approximate Regret-Matching Algorithms
• Alternative Function Approximation Parameterizations for Solving Games: An Analysis of $f$-Regression Counterfactual Regret Minimization
• Conic Blackwell Algorithm: Parameter-Free Convex-Concave Saddle-Point Solving
• Efficient Decentralized Learning Dynamics for Extensive-Form Coarse Correlated Equilibrium: No Expensive Computation of Stationary Distributions Required
• Convex-Concave Min-Max Stackelberg Games