MEAL: A Benchmark for Continual Multi-Agent Reinforcement Learning
Eindhoven University of Technology · University of Edinburgh · Universität Stuttgart · TU Eindhoven · King's College London · University of Stuttgart · University of Liverpool
PDF 由论文原始站点提供，PaperCompass 不保存论文文件。
摘要
Benchmarks play a central role in reinforcement learning (RL) research, yet their computational constraints often shape what is studied. Despite the motivation of lifelong learning, most continual RL papers consider only 3–10 sequential tasks, as CPU-bound environments make longer sequences impractical. Meanwhile, continual learning in cooperative multi-agent settings remains largely unexplored. To address these gaps, we introduce **MEAL** (**M**ulti-agent **E**nvironments for **A**daptive **L**earning), the first benchmark for continual multi-agent RL. By leveraging JAX and GPU acceleration, MEAL enables training on sequences of 100 tasks on a single GPU in a few hours. We find that long task sequences reveal failure modes that do not appear at smaller scales.