Advances in Multi-agent Reinforcement Learning: Persistent Autonomy and Robot Learning Lab Report 2024

TL;DR

This paper reviews recent advances in Multi-Agent Reinforcement Learning (MARL), focusing on challenges like non-stationarity and constraints, and discusses approaches developed at the PeARL lab to enhance multi-agent cooperation and autonomy.

Contribution

It provides an overview of novel MARL approaches from the PeARL lab, highlighting recent research directions and future prospects in multi-agent cooperation and autonomous systems.

Findings

Summarizes recent MARL methods addressing non-stationarity and constraints.

Highlights potential future research directions in MARL.

Showcases approaches developed at the PeARL lab for persistent autonomy.

Abstract

Multi-Agent Reinforcement Learning (MARL) approaches have emerged as popular solutions to address the general challenges of cooperation in multi-agent environments, where the success of achieving shared or individual goals critically depends on the coordination and collaboration between agents. However, existing cooperative MARL methods face several challenges intrinsic to multi-agent systems, such as the curse of dimensionality, non-stationarity, and the need for a global exploration strategy. Moreover, the presence of agents with constraints (e.g., limited battery life, restricted mobility) or distinct roles further exacerbates these challenges. This document provides an overview of recent advances in Multi-Agent Reinforcement Learning (MARL) conducted at the Persistent Autonomy and Robot Learning (PeARL) lab at the University of Massachusetts Lowell. We briefly discuss various research directions and present a selection of approaches proposed in our most recent publications. For each proposed approach, we also highlight potential future directions to further advance the field.