English

Is Nash Equilibrium Approximator Learnable?

Computer Science and Game Theory 2023-03-15 v6 Machine Learning Multiagent Systems

Abstract

In this paper, we investigate the learnability of the function approximator that approximates Nash equilibrium (NE) for games generated from a distribution. First, we offer a generalization bound using the Probably Approximately Correct (PAC) learning model. The bound describes the gap between the expected loss and empirical loss of the NE approximator. Afterward, we prove the agnostic PAC learnability of the Nash approximator. In addition to theoretical analysis, we demonstrate an application of NE approximator in experiments. The trained NE approximator can be used to warm-start and accelerate classical NE solvers. Together, our results show the practicability of approximating NE through function approximation.

Keywords

Cite

@article{arxiv.2108.07472,
  title  = {Is Nash Equilibrium Approximator Learnable?},
  author = {Zhijian Duan and Wenhan Huang and Dinghuai Zhang and Yali Du and Jun Wang and Yaodong Yang and Xiaotie Deng},
  journal= {arXiv preprint arXiv:2108.07472},
  year   = {2023}
}

Comments

Accepted by AAMAS 2023

R2 v1 2026-06-24T05:10:43.152Z