Skip to yearly menu bar Skip to main content


Poster

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

Jiawei Huang · Batuhan Yardim · Niao He

MR1 & MR2 - Number 13
[ ]
Thu 2 May 8 a.m. PDT — 8:30 a.m. PDT

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 $\epsilon$-optimal policy for MFC or an $\epsilon$-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.

Live content is unavailable. Log in and register to view live content