English

On the Statistical Efficiency of Mean-Field Reinforcement Learning with General Function Approximation

Machine Learning 2024-10-04 v5 Artificial Intelligence Machine Learning

Abstract

In this paper, we study the fundamental statistical efficiency of Reinforcement Learning in Mean-Field Control (MFC) and Mean-Field Game (MFG) with general model-based function approximation. We introduce a new concept called Mean-Field Model-Based Eluder Dimension (MF-MBED), which characterizes the inherent complexity of mean-field model classes. We show that a rich family of Mean-Field RL problems exhibits low MF-MBED. Additionally, we propose algorithms based on maximal likelihood estimation, which can return an ϵ\epsilon-optimal policy for MFC or an ϵ\epsilon-Nash Equilibrium policy for MFG. The overall sample complexity depends only polynomially on MF-MBED, which is potentially much lower than the size of state-action space. Compared with previous works, our results only require the minimal assumptions including realizability and Lipschitz continuity.

Keywords

Cite

@article{arxiv.2305.11283,
  title  = {On the Statistical Efficiency of Mean-Field Reinforcement Learning with General Function Approximation},
  author = {Jiawei Huang and Batuhan Yardim and Niao He},
  journal= {arXiv preprint arXiv:2305.11283},
  year   = {2024}
}

Comments

AISTATS 2024; 38 Pages

R2 v1 2026-06-28T10:38:40.673Z