English

Follower Agnostic Methods for Stackelberg Games

Optimization and Control 2024-03-28 v3 Artificial Intelligence Computer Science and Game Theory Dynamical Systems

Abstract

In this paper, we present an efficient algorithm to solve online Stackelberg games, featuring multiple followers, in a follower-agnostic manner. Unlike previous works, our approach works even when leader has no knowledge about the followers' utility functions or strategy space. Our algorithm introduces a unique gradient estimator, leveraging specially designed strategies to probe followers. In a departure from traditional assumptions of optimal play, we model followers' responses using a convergent adaptation rule, allowing for realistic and dynamic interactions. The leader constructs the gradient estimator solely based on observations of followers' actions. We provide both non-asymptotic convergence rates to stationary points of the leader's objective and demonstrate asymptotic convergence to a \emph{local Stackelberg equilibrium}. To validate the effectiveness of our algorithm, we use this algorithm to solve the problem of incentive design on a large-scale transportation network, showcasing its robustness even when the leader lacks access to followers' demand.

Keywords

Cite

@article{arxiv.2302.01421,
  title  = {Follower Agnostic Methods for Stackelberg Games},
  author = {Chinmay Maheshwari and James Cheng and S. Shankar Sasty and Lillian Ratliff and Eric Mazumdar},
  journal= {arXiv preprint arXiv:2302.01421},
  year   = {2024}
}

Comments

31 pages

R2 v1 2026-06-28T08:30:50.447Z