arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2005.03169eess.SYcs.SY
收藏

局部状态信息结构下折扣费用无穷时域Markov决策过程的最优控制

On Optimal Control of Discounted Cost Infinite-Horizon Markov Decision Processes Under Local State Information Structures

Guanze Peng, Veeraruna Kavitha, Qunayan Zhu

摘要:

研究了一类具有局部状态信息的马氏过程的最优控制问题。决策者只能局部访问状态向量信息的一个子集,这是多智能体系统中分散控制问题中经常遇到的问题。在这种信息结构下,部分状态向量不能被观测到。我们利用从头算原理,并找到了一种新的形式的贝尔曼方程来描述局部信息结构下的控制问题的最优策略。动态规划解决方案的特点是混合动力学相关的不可观测的状态组件和本地状态反馈政策的基础上,可观察的本地信息。我们进一步使用线性规划方法的最优局部状态反馈策略的特点。为了降低最优策略的计算复杂度,我们提出了一种基于虚拟信念的近似算法来寻找次优策略。我们展示了次优解的性能界限,并通过数值案例研究证实了结果。

英文摘要:

This paper investigates a class of optimal control problems associated with Markov processes with local state information. The decision-maker has only local access to a subset of a state vector information as often encountered in decentralized control problems in multi-agent systems. Under this information structure, part of the state vector cannot be observed. We leverage ab initio principles and find a new form of Bellman equations to characterize the optimal policies of the control problem under local information structures. The dynamic programming solutions feature a mixture of dynamics associated unobservable state components and the local state-feedback policy based on the observable local information. We further characterize the optimal local-state feedback policy using linear programming methods. To reduce the computational complexity of the optimal policy, we propose an approximate algorithm based on virtual beliefs to find a sub-optimal policy. We show the performance bounds on the sub-optimal solution and corroborate the results with numerical case studies.

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。

↑