English

Rate optimal learning of equilibria from data

Machine Learning 2025-10-13 v1 Artificial Intelligence

Abstract

We close open theoretical gaps in Multi-Agent Imitation Learning (MAIL) by characterizing the limits of non-interactive MAIL and presenting the first interactive algorithm with near-optimal sample complexity. In the non-interactive setting, we prove a statistical lower bound that identifies the all-policy deviation concentrability coefficient as the fundamental complexity measure, and we show that Behavior Cloning (BC) is rate-optimal. For the interactive setting, we introduce a framework that combines reward-free reinforcement learning with interactive MAIL and instantiate it with an algorithm, MAIL-WARM. It improves the best previously known sample complexity from O(ε8)\mathcal{O}(\varepsilon^{-8}) to O(ε2),\mathcal{O}(\varepsilon^{-2}), matching the dependence on ε\varepsilon implied by our lower bound. Finally, we provide numerical results that support our theory and illustrate, in environments such as grid worlds, where Behavior Cloning fails to learn.

Keywords

Cite

@article{arxiv.2510.09325,
  title  = {Rate optimal learning of equilibria from data},
  author = {Till Freihaut and Luca Viano and Emanuele Nevali and Volkan Cevher and Matthieu Geist and Giorgia Ramponi},
  journal= {arXiv preprint arXiv:2510.09325},
  year   = {2025}
}
R2 v1 2026-07-01T06:29:18.197Z