Distributed Influence-Augmented Local Simulators for Parallel MARL in Large Networked Systems

TL;DR

This paper introduces a method to decompose large networked multi-agent systems into local simulators with influence modeling, enabling faster training and improved stability in multi-agent reinforcement learning.

Contribution

It proposes a novel distributed simulation framework with influence-augmented local simulators for efficient parallel multi-agent reinforcement learning in complex systems.

Findings

Distributed simulation reduces training time to a few hours.

Parallel simulation mitigates negative effects of simultaneous learning.

Influence modeling improves the accuracy of local simulators.

Abstract

Due to its high sample complexity, simulation is, as of today, critical for the successful application of reinforcement learning. Many real-world problems, however, exhibit overly complex dynamics, which makes their full-scale simulation computationally slow. In this paper, we show how to decompose large networked systems of many agents into multiple local components such that we can build separate simulators that run independently and in parallel. To monitor the influence that the different local components exert on one another, each of these simulators is equipped with a learned model that is periodically trained on real trajectories. Our empirical results reveal that distributing the simulation among different processes not only makes it possible to train large multi-agent systems in just a few hours but also helps mitigate the negative effects of simultaneous learning.