Benchmarking MARL on long horizon sequential multi-objective tasks

• Main Authors: GENG, Minghong, PATERIA, Shubham, SUBAGDJA, Budhitama, TAN, Ah-Hwee
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2024
• Subjects: Multi-agent reinforcement learning; Multi-objective multi-agent reinforcement learning; Benchmark; Artificial Intelligence and Robotics
• Online Access: https://ink.library.smu.edu.sg/sis_research/9784; https://ink.library.smu.edu.sg/context/sis_research/article/10784/viewcontent/p2279__1_.pdf
• Institution: Singapore Management University

Current MARL benchmarks fall short in simulating realistic scenarios, particularly those involving long action sequences with sequential tasks and multiple conflicting objectives. Addressing this gap, we introduce Multi-Objective SMAC (MOSMAC), a novel MARL benchmark tailored to assess MARL methods on tasks with varying time horizons and multiple objectives. Each MOSMAC task contains one or multiple sequential subtasks. Agents are required to simultaneously balance between two objectives - combat and navigation - to successfully complete each subtask. Our evaluation of nine state-of-the-art MARL algorithms reveals that MOSMAC presents substantial challenges to many state-of-the-art MARL methods and effectively fills a critical gap in existing benchmarks for both single-objective and multi-objective MARL research.