Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

5-2025

Abstract

Recent advancements in multi-agent reinforcement learning (MARL) have demonstrated success on various cooperative multi-agent tasks. However, current benchmarks often fall short of representing realistic scenarios that demand agents to execute sequential tasks over long temporal horizons while balancing multiple objectives. To address this limitation, we introduce multi-objective SMAC (MOSMAC), a comprehensive MARL benchmark designed to evaluate MARL methods on tasks involving multiple objectives, sequential subtask assignments, and varying temporal horizons. MOSMAC requires agents to tackle a series of interconnected subtasks in StarCraft II while simultaneously optimizing for multiple objectives, including combat, safety, and navigation. Through rigorous evaluation of nine state-of-the-art MARL algorithms, we demonstrate that MOSMAC presents substantial challenges to existing methods, particularly in long-horizon scenarios. Our analysis establishes MOSMAC as an essential benchmark for bridging the gap between singleobjective MARL and multi-objective MARL (MOMARL). The codes for MOSMAC are available at: https://github.com/smu-ncc/mosmac.

Keywords

Benchmark, Multi-agent Reinforcement Learning, Multi-objective Multi-agent Reinforcement Learning

Discipline

Artificial Intelligence and Robotics

Areas of Excellence

Sustainability

Publication

AAMAS '25: Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems, Detroit, MI, USA, May 19-23

First Page

867

Last Page

876

ISBN

9798400714269

Identifier

10.5555/3709347.3743605

Publisher

ACM

City or Country

New York

Additional URL

https://dl.acm.org/doi/10.5555/3709347.3743605

Download

Share

COinS