多智能体路径规划（MAPF）问题旨在确定一组智能体在给定网络中为尽快到达各自目标地且互不碰撞而应遵循的轨迹。我们旨在最小化任意智能体到达目标所需的最长时间，以确保最优路径长度。在本研究中，我们通过参数化复杂度视角，补充了近期旨在系统研究该问题算法行为的一系列成果。首先，我们证明了当给定网络具有星型拓扑（有界顶点覆盖数）或是具有 $11$ 个叶子的树时，MAPF 是 NP-hard 的。这两项结果填补了我们对这一问题可处理性理解上的重要空白，这些空白在 [Fioravantes et al. Exact Algorithms and Lowerbounds for Multiagent Path Finding: Power of Treelike Topology. AAAI'24] 的近期工作中未被处理。然而，我们的主要贡献是提出了一种当给定网络拓扑高度集中化（有界距离到团）时，能随输入规模良好扩展的精确算法（FPT）。该参数意义重大，因为它反映了现实世界的网络。在这样的环境中，一群中心枢纽（例如，处理区域）仅连接到少数外围节点。
英文摘要：
The Mutliagent Path Finding (MAPF) problem consists of identifying the trajectories that a set of agents should follow inside a given network in order to reach their desired destinations as soon as possible, but without colliding with each other. We aim to minimize the maximum time any agent takes to reach their goal, ensuring optimal path length. In this work, we complement a recent thread of results that aim to systematically study the algorithmic behavior of this problem, through the parameterized complexity point of view.
First, we show that MAPF is NP-hard when the given network has a star-like topology (bounded vertex cover number) or is a tree with $11$ leaves. Both of these results fill important gaps in our understanding of the tractability of this problem that were left untreated in the recent work of [Fioravantes et al. Exact Algorithms and Lowerbounds for Multiagent Path Finding: Power of Treelike Topology. AAAI'24]. Nevertheless, our main contribution is an exact algorithm that scales well as the input grows (FPT) when the topology of the given network is highly centralized (bounded distance to clique). This parameter is significant as it mirrors real-world networks. In such environments, a bunch of central hubs (e.g., processing areas) are connected to only few peripheral nodes.
Multiagent Simple Temporal Problem: The Arc-Consistency Approach
Centre for Quantum Software and Information, FEIT, University of Technology Sydney（悉尼科技大学 FEIT 量子软件与信息中心）；UTS-AMSS Joint Research Laboratory, AMSS, Chinese Academy of Sciences（中国科学院数学与系统科学研究院 UTS-AMSS 联合研究实验室）
Learning Heterogeneous Agent Cooperation via Multiagent League Training
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）
Diverse Auto-Curriculum is Critical for Successful Real-World Multiagent Learning Systems
University College London（伦敦大学学院）；Huawei R&D U.K.（华为英国研发部）；Huawei Canada（华为加拿大公司）；Shanghai Jiao Tong University（上海交通大学）；University of Alberta（阿尔伯塔大学）；Alberta Machine Intelligence Institute（阿尔伯塔机器智能研究所）
On Improving Model-Free Algorithms for Decentralized Multi-Agent Reinforcement Learning
University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；DeepMind（深度思维）；Massachusetts Institute of Technology（麻省理工学院）
多智能体强化学习（MARL）算法经常遭受指数样本复杂度对智能体数量的依赖，这种现象被称为\emph{the curse of multiagents}。在本文中，我们解决这一挑战，调查样本效率的无模型算法在\emph{decentralized} MARL，并旨在改善现有的算法沿这条线。对于学习（粗）一般和马尔可夫博弈中的相关均衡，我们提出了\emph{stage-based} V-学习算法，大大简化了最近的作品的算法设计和分析，并规避了一个相当复杂的无\emph{weighted}遗憾强盗子程序。针对马尔可夫势博弈中纳什均衡的学习问题，提出了一种独立的策略梯度算法，该算法采用分散的基于动量的方差缩减技术。我们所有的算法都是去中心化的，因为每个代理只能根据其本地信息做出决策。在学习过程中既不需要通信，也不需要集中协调，从而导致对大量代理的自然泛化。我们还提供了数值模拟来证实我们的理论研究结果。
Peoples’ Friendship University of Russia (RUDN University)（俄罗斯人民友谊大学）；Federal Research Center for 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）；HSE University（高等经济学院）；Ben-Gurion University of the Negev（内盖夫本-古里安大学）；Palo Alto Research Center（帕洛阿尔托研究中心）
A Particle Swarm Inspired Approach for Continuous Distributed Constraint Optimization Problems
Department of Computer Science and Engineering, University of Dhaka（达卡大学计算机科学与工程系）；Department of Computer Science and Engineering, Washington University in St. Louis（圣路易斯华盛顿大学计算机科学与工程系）
