arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2312.07862math.OC
收藏

动态信息操纵博弈

Dynamic Information Manipulation Game

Shutian Liu, Quanyan Zhu

AI总结:

提出动态信息操纵博弈(DIMG),研究信息操纵者隐蔽设计POMDP联合状态分布以影响下层控制器动作的分层机制,并通过阶段约束和信念扭曲分析其对控制策略性能的影响。

摘要:

我们提出动态信息操纵博弈(DIMG),以研究信息操纵者(IM)影响部分可观察马尔可夫决策过程(POMDP)转移规则的激励。DIMG是一种分层博弈,上层IM隐蔽地设计POMDP的联合状态分布,以影响下层控制器的动作。DIMG的基本特征由阶段约束刻画,该约束确保被操纵核与原始核的不可观测边缘分布之间的一致性。在信息扭曲的均衡中,IM最小化累积成本,该成本取决于控制器由POMDP最优策略生成的、受信息操纵的动作。我们讨论了事前和事中操纵方案,并展示了它们的联系。通过操纵对信念扭曲的影响,分析了操纵对控制策略性能的影响。

英文摘要:

We propose a dynamic information manipulation game (DIMG) to investigate the incentives of an information manipulator (IM) to influence the transition rules of a partially observable Markov decision process (POMDP). DIMG is a hierarchical game where the upper-level IM stealthily designs the POMDP's joint state distributions to influence the lower-level controller's actions. DIMG's fundamental feature is characterized by a stagewise constraint that ensures the consistency between the unobservable marginals of the manipulated and the original kernels. In an equilibrium of information distortion, the IM minimizes cumulative cost that depends on the controller's informationally manipulated actions generated by the optimal policy to the POMDP. We discuss ex ante and interim manipulation schemes and show their connections. The effect of manipulation on the performance of control policies is analyzed through its influence on belief distortion.

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。

↑