English

Anytime-Constrained Equilibria in Polynomial Time

Machine Learning 2025-03-05 v2 Artificial Intelligence Data Structures and Algorithms Computer Science and Game Theory

Abstract

We extend anytime constraints to the Markov game setting and the corresponding solution concept of an anytime-constrained equilibrium (ACE). Then, we present a comprehensive theory of anytime-constrained equilibria that includes (1) a computational characterization of feasible policies, (2) a fixed-parameter tractable algorithm for computing ACE, and (3) a polynomial-time algorithm for approximately computing ACE. Since computing a feasible policy is NP-hard even for two-player zero-sum games, our approximation guarantees are optimal so long as PNPP \neq NP. We also develop the first theory of efficient computation for action-constrained Markov games, which may be of independent interest.

Keywords

Cite

@article{arxiv.2410.23637,
  title  = {Anytime-Constrained Equilibria in Polynomial Time},
  author = {Jeremy McMahan},
  journal= {arXiv preprint arXiv:2410.23637},
  year   = {2025}
}
R2 v1 2026-06-28T19:42:24.408Z