Decentralized Multi-Agent Reinforcement Learning with Global State Prediction

TL;DR

This paper investigates decentralized multi-agent reinforcement learning for robot swarms, introducing a global state prediction network to improve performance without relying on global information, demonstrated through collective transport tasks.

Contribution

The paper proposes Global State Prediction (GSP), a novel network that predicts swarm states, enhancing decentralized learning and robustness in multi-agent systems without global knowledge.

Findings

GSP improves success rates in collective transport tasks.

Including GSP increases robustness against obstacles.

Decentralized methods with GSP outperform those without global information.

Abstract

Deep reinforcement learning (DRL) has seen remarkable success in the control of single robots. However, applying DRL to robot swarms presents significant challenges. A critical challenge is non-stationarity, which occurs when two or more robots update individual or shared policies concurrently, thereby engaging in an interdependent training process with no guarantees of convergence. Circumventing non-stationarity typically involves training the robots with global information about other agents' states and/or actions. In contrast, in this paper we explore how to remove the need for global information. We pose our problem as a Partially Observable Markov Decision Process, due to the absence of global knowledge on other agents. Using collective transport as a testbed scenario, we study two approaches to multi-agent training. In the first, the robots exchange no messages, and are trained to rely on implicit communication through push-and-pull on the object to transport. In the second approach, we introduce Global State Prediction (GSP), a network trained to forma a belief over the swarm as a whole and predict its future states. We provide a comprehensive study over four well-known deep reinforcement learning algorithms in environments with obstacles, measuring performance as the successful transport of the object to the goal within a desired time-frame. Through an ablation study, we show that including GSP boosts performance and increases robustness when compared with methods that use global knowledge.