LGAIGTMAMay 5, 2024

A Single Online Agent Can Efficiently Learn Mean Field Games

MIT
arXiv:2405.03718v22 citationsh-index: 10ECAI
Originality Highly original
AI Analysis

This addresses the problem of solving MFGs in large-population systems for researchers and practitioners, offering a more practical approach compared to traditional methods.

The paper tackles the challenge of solving mean field games (MFGs) by introducing a novel online single-agent model-free learning scheme that enables efficient learning of mean field Nash equilibria using online samples, with sample complexity guarantees and confirmed efficacy in numerical experiments.

Mean field games (MFGs) are a promising framework for modeling the behavior of large-population systems. However, solving MFGs can be challenging due to the coupling of forward population evolution and backward agent dynamics. Typically, obtaining mean field Nash equilibria (MFNE) involves an iterative approach where the forward and backward processes are solved alternately, known as fixed-point iteration (FPI). This method requires fully observed population propagation and agent dynamics over the entire spatial domain, which could be impractical in some real-world scenarios. To overcome this limitation, this paper introduces a novel online single-agent model-free learning scheme, which enables a single agent to learn MFNE using online samples, without prior knowledge of the state-action space, reward function, or transition dynamics. Specifically, the agent updates its policy through the value function (Q), while simultaneously evaluating the mean field state (M), using the same batch of observations. We develop two variants of this learning scheme: off-policy and on-policy QM iteration. We prove that they efficiently approximate FPI, and a sample complexity guarantee is provided. The efficacy of our methods is confirmed by numerical experiments.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes