arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.01568cs.GTcs.RO
收藏

高效求解混合层级游戏的准策略近似方法

Efficiently Solving Mixed-Hierarchy Games with Quasi-Policy Approximations

University of Texas at Austin(德克萨斯大学奥斯汀分校);U.S. Army Research Laboratory(美国陆军研究实验室)

Hamzah Khan, Dong Ho Lee, Jingqi Li, Tianyu Qiu, Christian Ellis, Jesse Milzman, Wesley Suttle, David Fridovich-Keil

AI总结:

本文研究了多机器人森林结构混合层级游戏,通过推导KKT条件并引入准策略近似方法,提出了一种求解高阶导数的非精确牛顿法,证明了在非二次目标和非线性约束下的局部指数收敛性。

摘要:

多机器人协调通常具有分层结构,一些机器人的决策依赖于其他机器人的计划行为。尽管博弈论为这类交互提供了系统框架,但现有求解器难以处理混合信息结构,即同时(纳什)和分层(斯塔克尔伯格)决策的结合。我们研究了N个机器人森林结构混合层级游戏,其中每个机器人在其子树中作为斯塔克尔伯格领导者,而不同分支的机器人通过纳什均衡互动。我们推导了此类游戏的库奇-库恩-图克(KKT)一阶最优性条件,并证明它们涉及随着层级深度增加而递增的高阶机器人最佳响应策略导数,使得直接求解不可行。为克服这一挑战,我们引入了准策略近似方法,以消除高阶策略导数,并开发了一种非精确牛顿法来高效求解由此产生的近似KKT系统。我们证明了对于非二次目标和非线性约束的游戏,所提出算法具有局部指数收敛性。该方法在高度优化的Julia库(MixedHierarchyGames.jl)中实现,并在硬件和模拟多智能体实验中评估,展示了对复杂混合层级信息结构的实时收敛性。

英文摘要:

Multi-robot coordination often exhibits hierarchical structure, with some robots' decisions depending on the planned behaviors of others. While game theory provides a principled framework for such interactions, existing solvers struggle to handle mixed information structures that combine simultaneous (Nash) and hierarchical (Stackelberg) decision-making. We study N-robot forest-structured mixed-hierarchy games, in which each robot acts as a Stackelberg leader over its subtree while robots in different branches interact via Nash equilibria. We derive the Karush-Kuhn-Tucker (KKT) first-order optimality conditions for this class of games and show that they involve increasingly high-order derivatives of robots' best-response policies as the hierarchy depth grows, rendering a direct solution intractable. To overcome this challenge, we introduce a quasi-policy approximation that removes higher-order policy derivatives and develop an inexact Newton method for efficiently solving the resulting approximated KKT systems. We prove local exponential convergence of the proposed algorithm for games with non-quadratic objectives and nonlinear constraints. The approach is implemented in a highly optimized Julia library (MixedHierarchyGames.jl) and evaluated in hardware and simulated multi-agent experiments, demonstrating real-time convergence for complex mixed-hierarchy information structures.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑