论文标题
一般总和随机游戏，带有网络信息流
General sum stochastic games with networked information flows
论文作者
论文摘要
受诸如供应链管理，流行病和社交网络等应用程序的启发，我们制定了一个随机游戏模型，该模型解决了这些领域中常见的三个关键特征：1）网络结构化播放器互动，2）播放器之间的配对混合合作和竞争，以及3）有限的全球信息限制全球决策。结合起来，这些特征对基于深度学习的多项式增强学习（MARL）算法采取的黑匣子方法构成了重大挑战，并且值得进行更详细的分析。我们通过配对的一般总和目标和不对称信息结构制定了一个网络随机游戏，并经验探索了信息可用性对不同MARL范式的结果（例如个别学习和集中学习分散执行执行）的影响。
Inspired by applications such as supply chain management, epidemics, and social networks, we formulate a stochastic game model that addresses three key features common across these domains: 1) network-structured player interactions, 2) pair-wise mixed cooperation and competition among players, and 3) limited global information toward individual decision-making. In combination, these features pose significant challenges for black box approaches taken by deep learning-based multi-agent reinforcement learning (MARL) algorithms and deserve more detailed analysis. We formulate a networked stochastic game with pair-wise general sum objectives and asymmetrical information structure, and empirically explore the effects of information availability on the outcomes of different MARL paradigms such as individual learning and centralized learning decentralized execution.
