Robust Stackelberg Equilibria

TL;DR

This paper introduces the robust Stackelberg equilibrium (RSE), a generalized solution concept for Stackelberg games that accounts for suboptimal follower responses, providing new insights into its properties, algorithms, and learnability.

Contribution

It defines the RSE, proves its existence, analyzes its properties, develops a quasi-polynomial approximation scheme, and studies its learnability, extending robustness concepts in Stackelberg games.

Findings

RSE always exists and is well-defined.

Computing an FPTAS for RSE is NP-hard, but a QPTAS is possible.

Learnability results improve existing algorithms for SSE.

Abstract

This paper provides a systematic study of the robust Stackelberg equilibrium (RSE), which naturally generalizes the widely adopted solution concept of the strong Stackelberg equilibrium (SSE). The RSE accounts for any possible up-to-$\delta$ suboptimal follower responses in Stackelberg games and is adopted to improve the robustness of the leader's strategy. While a few variants of robust Stackelberg equilibrium have been considered in previous literature, the RSE solution concept we consider is importantly different -- in some sense, it relaxes previously studied robust Stackelberg strategies and is applicable to much broader sources of uncertainties. We provide a thorough investigation of several fundamental properties of RSE, including its utility guarantees, algorithmics, and learnability. We first show that the RSE we defined always exists and thus is well-defined. Then we characterize how the leader's utility in RSE changes with the robustness level considered. On the algorithmic side, we show that, in sharp contrast to the tractability of computing an SSE, it is NP-hard to obtain a fully polynomial approximation scheme (FPTAS) for any constant robustness level. Nevertheless, we develop a quasi-polynomial approximation scheme (QPTAS) for RSE. Finally, we examine the learnability of the RSE in a natural learning scenario, where both players' utilities are not known in advance, and provide almost tight sample complexity results on learning the RSE. As a corollary of this result, we also obtain an algorithm for learning SSE, which strictly improves a key result of Bai et al. [2021] in terms of both utility guarantee and computational efficiency.