首个支持百任务持续学习的多智能体强化学习基准
MEAL: A Benchmark for Continual Multi-Agent Reinforcement Learning
- 基于JAX与GPU加速，实现单卡数小时完成百任务训练
- 发现长序列任务中暴露了短序列下无法察觉的失败模式
- 适合研究持续学习、多智能体协作的科研人员
基准测试在强化学习研究中起核心作用，但计算限制常决定研究方向。尽管终身学习具有吸引力，多数持续强化学习论文仅考虑3-10个连续任务，因依赖CPU的环境使更长序列难以实现。同时，合作多智能体场景下的持续学习仍基本未被探索。为此，我们提出MEAL（Multi-agent Environments for Adaptive Learning），首个面向持续多智能体强化学习的基准。通过采用JAX和GPU加速，MEAL可在单张GPU上数小时内完成100个任务序列的训练。我们发现，长任务序列暴露出在小规模下不会显现的失败模式。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。