用元强化学习让系统快速适应负载变化，减少重训练。
Meta-Reinforcement Learning with Discrete World Models for Adaptive Load Balancing
- 结合元强化学习与DreamerV3架构，实现快速自适应。
- 在标准和动态测试中均优于A2C算法，性能更稳定。
- 抗灾难性遗忘，适合复杂多变的系统管理场景。
我们将元强化学习算法与DreamerV3架构相结合，以提升操作系统的负载均衡能力。该方法能在极少重训练的情况下快速适应动态工作负载，在标准和自适应测试中均优于优势演员-评论家（A2C）算法。实验表明，该方法对灾难性遗忘具有强鲁棒性，在不同工作负载分布和规模下均能保持高性能。研究结果对优化现代操作系统的资源管理和性能表现具有重要意义。通过应对动态异构工作负载的挑战，该方法显著提升了强化学习在真实系统管理任务中的适应性与效率。
原文摘要 · Abstract (English)
We integrate a meta-reinforcement learning algorithm with the DreamerV3 architecture to improve load balancing in operating systems. This approach enables rapid adaptation to dynamic workloads with minimal retraining, outperforming the Advantage Actor-Critic (A2C) algorithm in standard and adaptive trials. It demonstrates robust resilience to catastrophic forgetting, maintaining high performance under varying workload distributions and sizes. These findings have important implications for optimizing resource management and performance in modern operating systems. By addressing the challenges posed by dynamic and heterogeneous workloads, our approach advances the adaptability and efficiency of reinforcement learning in real-world system management tasks.
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。