Work

Joint Intrinsic Motivation for Coordinated Exploration in Multi-Agent Deep Reinforcement Learning

Year: 2024

Type: conference-paper

Abstract: Multi-agent deep reinforcement learning (MADRL) often struggles to learn strongly coordinated tasks, as performance depends not only on one agent's behavior but rather on the joint behavior of multiple agents. In this context, a group of agents can benefit from actively exploring different joint strategies to determine the most efficient one. In this paper, we propose an approach for rewarding strategies where agents collectively exhibit novel behaviors. We present JIM (Joint Intrinsic Motivation), a multi-agent intrinsic motivation method that rewards joint trajectories based on a centralized measure of novelty. We show how JIM can be used to improve state-of-the-art MADRL methods in a highly coordinated task, demonstrating the crucial role of coordinated exploration.

Source: Adaptive Agents and Multi-Agents Systems

DOI: 10.65109/iuhq8304

Authors: Maxime Toquebiau, Nicolas Bredeche, Faïz Benamar, Jae-Yun Jun

Institutions: Centre National de la Recherche Scientifique, Sorbonne Université, École Centrale d'Électronique, Institut Systèmes Intelligents et de Robotique

Language: English

Topic: Reinforcement Learning in Robotics

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W7124258685

FWCI: 0.305

Cites: 7

Cited by: 2

Related to: 10