论文标题
大规模多代理深FBSDE
Large-Scale Multi-Agent Deep FBSDEs
论文作者
论文摘要
在本文中，我们提出了一个可扩展的深度学习框架，用于使用虚拟游戏在多代理随机游戏中找到马尔可夫·纳什（Markovian Nash）平衡。动机的灵感来自对向后的随机微分方程（FBSDE）的理论分析及其在深度学习环境中的实施，这是我们算法的样本效率提高的来源。通过利用代理在对称游戏中的置换式属性的优势，可扩展性和性能得到了显着提高。我们在多个指标方面展示了与最先进的深层虚拟戏剧算法相比，我们的框架表现出色。更重要的是，我们的方法在模拟中最多可以扩展3000个代理，据我们所知，该量表代表了一个新的最新技术。我们还证明了我们在机器人技术中的适用性在信仰空间自主赛车问题上。
In this paper we present a scalable deep learning framework for finding Markovian Nash Equilibria in multi-agent stochastic games using fictitious play. The motivation is inspired by theoretical analysis of Forward Backward Stochastic Differential Equations (FBSDE) and their implementation in a deep learning setting, which is the source of our algorithm's sample efficiency improvement. By taking advantage of the permutation-invariant property of agents in symmetric games, the scalability and performance is further enhanced significantly. We showcase superior performance of our framework over the state-of-the-art deep fictitious play algorithm on an inter-bank lending/borrowing problem in terms of multiple metrics. More importantly, our approach scales up to 3000 agents in simulation, a scale which, to the best of our knowledge, represents a new state-of-the-art. We also demonstrate the applicability of our framework in robotics on a belief space autonomous racing problem.
