Sample-Efficient Learning of Stackelberg Equilibria in General-Sum Games

Yu Bai, Chi Jin, Huan Wang, Caiming Xiong

Keywords: Stackelberg equilibria, general-sum games, reinforcement learning theory, multi-agent RL

Abstract:

Real world applications such as economics and policy making often involve solving multi-agent games with two unique features: (1) The agents are inherently *asymmetric* and partitioned into leaders and followers; (2) The agents have different reward functions, thus the game is *general-sum*. The majority of existing results in this field focuses on either symmetric solution concepts (e.g. Nash equilibrium) or zero-sum games. It remains open how to learn the *Stackelberg equilibrium*---an asymmetric analog of the Nash equilibrium---in general-sum games efficiently from noisy samples.
This paper initiates the theoretical study of sample-efficient learning of the Stackelberg equilibrium, in the bandit feedback setting where we only observe noisy samples of the reward. We consider three representative two-player general-sum games: bandit games, bandit-reinforcement learning (bandit-RL) games, and linear bandit games. In all these games, we identify a fundamental gap between the exact value of the Stackelberg equilibrium and its estimated version using finitely many noisy samples, which can not be closed information-theoretically regardless of the algorithm. We then establish sharp positive results on sample-efficient learning of Stackelberg equilibrium with value optimal up to the gap identified above, with matching lower bounds in the dependency on the gap, error tolerance, and the size of the action spaces. Overall, our results unveil unique challenges in learning Stackelberg equilibria under noisy bandit feedback, which we hope could shed light on future research on this topic.

Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.

TL;DR: We provide the first line of theoretical results for learning Stackelberg equilibria from noisy bandit feedback of the rewards in general-sum games.