Year: 2025
Type: preprint
Abstract: 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 (Multi-agent Environments for Adaptive Learning), the first benchmark for continual multi-agent RL. By leveraging JAX and GPU acceleration, MEAL enables training on sequences of 100 tasks in a few hours on a single GPU. We find that long task sequences reveal failure modes that do not appear at smaller scales.
Source: arXiv (Cornell University)
Authors: Tomilin, Tristan, Boogaard, Luka van den, Garcin, Samuel, Ruhdorfer, Constantin, Grooten, Bram, Kusters, Fabrice, Du, Yali, Bulling, Andreas, Pechenizkiy, Mykola, Fang, Meng
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4415333307
Cites:
Cited by:
Related to: