Sequential Decision Making in Decentralized Systems
Sequential Decision Making in Decentralized Systems
复制标题
去中心化系统中的顺序决策
DOI：
--
复制
发表时间：
2011
期刊：
影响因子：
--
通讯作者：
A. Nayyar
中科院分区：
文献类型：
--
作者：
A. Nayyar
分散系统中的顺序决策Ashutosh Nayyar主席：Demosthenis Teneketzis我们研究合作系统中的顺序决策问题，其中具有不同信息的不同代理想要实现共同目标。决策问题的顺序性意味着所有的决策都可以按顺序排列，使得做出第t个决策的信息只取决于前面的决策。马尔可夫决策理论提供了解决经典信息结构的顺序决策问题的工具。在这篇论文中，我们介绍了一种新的方法来解决非经典信息结构的决策问题。这种方法依赖于决策者之间的共同信息的想法。直觉上，共同信息包括过去的观察和决策，这些都是当前和未来决策者所熟知的。我们表明，一个共同的信息为基础的方法可以让我们发现新的结构的最优决策策略的结果，并提供一个顺序分解的决策问题。我们首先证明了这种方法的两个具体情况下的顺序问题，即，一个实时的多终端通信系统和一个分散的控制系统延迟共享信息。然后，我们表明，共同信息方法更普遍地适用于任何
Sequential Decision Making in Decentralized Systems by Ashutosh Nayyar Chair: Demosthenis Teneketzis We study sequential decision making problems in cooperative systems where different agents with different information want to achieve a common objective. The sequential nature of the decision problem implies that all decisions can be arranged in a sequence such that the information available to make the t decision only depends on preceding decisions. Markov decision theory provides tools for addressing sequential decision making problems with classical information structures. In this thesis, we introduce a new approach for decision making problems with non-classical information structures. This approach relies on the idea of common information between decision-makers. Intuitively, common information consists of past observations and decisions that are commonly known to the current and future decision makers. We show that a common information based approach can allow us to discover new structural results of optimal decision strategies and provide a sequential decomposition of the decision-making problems. We first demonstrate this approach on two specific instances of sequential problems, namely, a real-time multi-terminal communication system and a decentralized control system with delayed sharing of information. We then show that the common information methodology applies more generally to any