Influence-Augmented Local Simulators: A Scalable Solution for Fast Deep RL in Large Networked Systems

TL;DR

This paper introduces influence-augmented local simulators that enable fast, scalable deep reinforcement learning in large networked systems by combining local models with learned global influence effects.

Contribution

The paper proposes a novel approach that integrates influence-augmented local simulators with deep RL to efficiently handle large, complex environments.

Findings

Significantly accelerates deep RL training in large systems

Effectively models global influence through learned local simulators

Offers a scalable solution for real-world RL applications

Abstract

Learning effective policies for real-world problems is still an open challenge for the field of reinforcement learning (RL). The main limitation being the amount of data needed and the pace at which that data can be obtained. In this paper, we study how to build lightweight simulators of complicated systems that can run sufficiently fast for deep RL to be applicable. We focus on domains where agents interact with a reduced portion of a larger environment while still being affected by the global dynamics. Our method combines the use of local simulators with learned models that mimic the influence of the global system. The experiments reveal that incorporating this idea into the deep RL workflow can considerably accelerate the training process and presents several opportunities for the future.