Decentralized control of cooperative systems captures the operation of a group of decision makers that share a single global objective. The difficulty in solving optimally such problems arises when the agents lack full observability of the global state of the system when they operate. The general problem has been shown to be NEXP-complete. In this paper, we identify classes of decentralized control problems whose complexity ranges between NEXP and P. In particular, we study problems characterized by independent transitions, independent observations, and goal-oriented objective functions. Two algorithms are shown to solve optimally useful classes of goal-oriented decentralized processes in polynomial time. This paper also studies information sharing among the decision-makers, which can improve their performance. We distinguish between three ways in which agents can exchange information: indirect communication, direct communication and sharing state features that are not controlled by the agents. Our analysis shows that for every class of problems we consider, introducing direct or indirect communication does not change the worst-case complexity. The results provide a better understanding of the complexity of decentralized control problems that arise in practice and facilitate the development of planning algorithms for these problems.
F2A2: Flexible Fully-decentralized Approximate Actor-critic for Cooperative Multi-agent Reinforcement Learning
The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Shenzhen Institute of Artificial Intelligence and Robotics for Society（深圳市人工智能与机器人研究院）；Tongji University（同济大学）；Shanghai Research Institute for Intelligent Autonomous Systems（上海智能自主系统研究院）；East China Normal University（华东师范大学）；Shanghai Jiao Tong University（上海交通大学）
Consensus Learning for Cooperative Multi-Agent Reinforcement Learning
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
Towards Global Optimality in Cooperative MARL with the Transformation And Distillation Framework
Washington University in St. Louis（华盛顿大学圣路易斯分校）；Institute for Interdisciplinary Information Sciences, Tsinghua University（清华大学交叉信息研究院）；Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）
Applying MAPP Algorithm for Cooperative Path Finding in Urban Environments
Federal Research Center “Computer Science and Control” of Russian Academy of Sciences（俄罗斯科学院“计算机科学与控制”联邦研究中心）；People’s Friendship University of Russia (RUDN University)（俄罗斯人民友谊大学）；National Research University Higher School of Economics（国家研究型高等经济大学）
Structured Cooperative Learning with Graphical Model Priors
University of Science and Technology of China（中国科学技术大学）；University of Maryland, College Park（马里兰大学帕克分校）；The University of Sydney（悉尼大学）；Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（合肥综合性国家科学中心人工智能研究院）
McGill University（麦吉尔大学）；Mila；Université de Montréal（蒙特利尔大学）；DeepMind
在本文中，我们研究学习时间抽象的合作多智能体系统，使用的选项框架（萨顿等，1999年）。首先，我们解决的分散POMDP的多智能体系统所代表的规划问题，通过引入一个\emph{common information approach}。我们使用\emph{common beliefs}和广播的概念来解决一个等价的集中式POMDP问题。然后，我们提出了分布式期权评价（DOC）算法，它使用集中式期权评价和分散式期权内改进。我们从理论上分析了DOC的渐近收敛性，并建立了一个新的多智能体环境，以证明其有效性。我们的实验经验表明，DOC执行竞争力对基线和规模的代理商的数量。
Cooperative Network Learning for Large-Scale and Decentralized Graphs
Institute of Fundamental and Frontier Sciences, University of Electronic Science and Technology of China（电子科技大学基础与前沿研究院）；Yangtze Delta Region Institute (Huzhou), University of Electronic Science and Technology of China（电子科技大学长三角研究院（湖州））；School of Cyber Science and Technology, University of Science and Technology of China（中国科学技术大学网络空间安全学院）
Cooperative Informative Sensing for Monitoring Dynamic Indoor Environments via Multi-Agent Reinforcement Learning
Korea Advanced Institute of Science and Technology（韩国科学技术院）；Stanford University（斯坦福大学）；University of California, Berkeley（加州大学伯克利分校）；University of California, Riverside（加州大学河滨分校）
From Explicit Communication to Tacit Cooperation:A Novel Paradigm for Cooperative MARL
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
