MFC-EQ: Mean-Field Control with Envelope Q-Learning for Moving Decentralized Agents in Formation

TL;DR

This paper introduces MFC-EQ, a scalable decentralized learning framework for multi-agent formation control that balances collision avoidance and formation maintenance, outperforming existing methods in complex, dynamic scenarios.

Contribution

The paper presents MFC-EQ, a novel mean-field control with envelop Q-learning approach enabling scalable, adaptable, and preference-agnostic multi-agent formation planning under partial observation.

Findings

MFC-EQ outperforms state-of-the-art centralized baselines.

It effectively manages dynamic formation changes.

The method scales well with increasing number of agents.

Abstract

We study a decentralized version of Moving Agents in Formation (MAiF), a variant of Multi-Agent Path Finding aiming to plan collision-free paths for multiple agents with the dual objectives of reaching their goals quickly while maintaining a desired formation. The agents must balance these objectives under conditions of partial observation and limited communication. The formation maintenance depends on the joint state of all agents, whose dimensionality increases exponentially with the number of agents, rendering the learning process intractable. Additionally, learning a single policy that can accommodate different linear preferences for these two objectives presents a significant challenge. In this paper, we propose Mean-Field Control with Envelop $Q$-learning (MFC-EQ), a scalable and adaptable learning framework for this bi-objective multi-agent problem. We approximate the dynamics of all agents using mean-field theory while learning a universal preference-agnostic policy through envelop $Q$-learning. Our empirical evaluation of MFC-EQ across numerous instances shows that it outperforms state-of-the-art centralized MAiF baselines. Furthermore, MFC-EQ effectively handles more complex scenarios where the desired formation changes dynamically -- a challenge that existing MAiF planners cannot address.