arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1206.6866cs.MAcs.SYeess.SYmath.OC
收藏

连续时空多智能体系统中的随机最优控制

Stochastic Optimal Control in Continuous Space-Time Multi-Agent Systems

SNN, Radboud University(Radboud大学)

Wim Wiegerinck, Bart van den Broek, Hilbert Kappen

AI总结:

将随机最优控制理论应用于协作多智能体系统,通过组合独立单智能体单目标最优控制并加权端部成本,将多智能体控制转化为图模型推理问题。

摘要:

最近,针对连续时空非线性动力系统中的随机最优控制理论已被发展(Kappen, 2005)。我们将该理论应用于协作多智能体系统。智能体根据给定的非线性动力学演化,并带有加性维纳噪声。每个智能体可以控制自身的动力学。目标是最小化累积联合成本,该成本由状态相关项和控制二次项组成。我们关注非交互智能体系统,这些智能体需要在一组针对不同智能体-目标组合的端部成本下,最优地分布在多个目标上。我们证明,最优控制是独立单智能体单目标最优控制的组合和,每个控制乘以与不同组合端部成本成比例的权重。因此,多智能体控制与标准图模型推理问题相关。与单智能体控制相比,额外的计算成本与指定组合和的图的树宽乘以目标数量成指数关系。我们通过对多达42个智能体的系统进行仿真来展示结果。

英文摘要:

Recently, a theory for stochastic optimal control in non-linear dynamical systems in continuous space-time has been developed (Kappen, 2005). We apply this theory to collaborative multi-agent systems. The agents evolve according to a given non-linear dynamics with additive Wiener noise. Each agent can control its own dynamics. The goal is to minimize the accumulated joint cost, which consists of a state dependent term and a term that is quadratic in the control. We focus on systems of non-interacting agents that have to distribute themselves optimally over a number of targets, given a set of end-costs for the different possible agent-target combinations. We show that optimal control is the combinatorial sum of independent single-agent single-target optimal controls weighted by a factor proportional to the end-costs of the different combinations. Thus, multi-agent control is related to a standard graphical model inference problem. The additional computational cost compared to single-agent control is exponential in the tree-width of the graph specifying the combinatorial sum times the number of targets. We illustrate the result by simulations of systems with up to 42 agents.

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。

↑