Multi-Agent Reinforcement Learning (MARL) is an increasingly important research field that can model and control multiple large-scale autonomous systems. Despite its achievements, existing multi-agent learning methods typically involve expensive computations in terms of training time and power arising from large observation-action space and a huge number of training steps. Therefore, a key challenge is understanding and characterizing the computationally intensive functions in several popular classes of MARL algorithms during their training phases. Our preliminary experiments reveal new insights into the key modules of MARL algorithms that limit the adoption of MARL in real-world systems. We explore neighbor sampling strategy to improve cache locality and observe performance improvement ranging from 26.66% (3 agents) to 27.39% (12 agents) during the computationally intensive mini-batch sampling phase. Additionally, we demonstrate that improving the locality leads to an end-to-end training time reduction of 10.2% (for 12 agents) compared to existing multi-agent algorithms without significant degradation in the mean reward.

翻译：多智能体强化学习（MARL）是一个日益重要的研究领域，能够建模并控制多个大规模自主系统。尽管已取得诸多成果，现有智能体学习方法通常因巨大的观察-行动空间和大量的训练步骤，在训练时间和功耗方面涉及昂贵的计算开销。因此，关键挑战在于理解并刻画若干主流MARL算法在训练阶段的计算密集型函数。我们的初步实验揭示了MARL算法中制约其在实际系统中部署的关键模块的新见解。本文探索采用邻居采样策略以提升缓存局部性，并在计算密集的小批量采样阶段观察到性能提升幅度从26.66%（3个智能体）到27.39%（12个智能体）。此外，我们证明，与现有智能体算法相比，提升局部性可使端到端训练时间减少10.2%（针对12个智能体），且平均奖励无明显下降。