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 2407.18635math.PRmath.OC
收藏

非可交换系统的Mean-field控制

Mean-field control of non exchangeable systems

Anna De Crescenzo, Marco Fuhrman, Idris Kharroubi, Huyên Pham

AI总结:

研究具有异质和非对称相互作用的Mean-field系统的最优控制,证明值函数的适定性与律不变性,结合动态规划原理与链式法则,证明值函数是Bellman动态规划方程的粘性解。

摘要:

我们研究具有异质和非对称相互作用的Mean-field系统的最优控制。这导致考虑一族受控Brownian扩散过程,其动力学依赖于整个边缘概率律集合。我们证明了此类系统的适定性,定义了控制问题及其相关的值函数。接着,我们证明了值函数的律不变性,这使我们能够在概率律集合上进行研究。我们表明值函数在概率测度集合的流上满足动态规划原理(DPP)。我们还推导了扩散过程的边缘律流上一类正则函数的链式法则。结合DPP和链式法则,我们证明值函数是Wasserstein空间值函数的$L^2$集合中Bellman动态规划方程的粘性解。

英文摘要:

We study the optimal control of mean-field systems with heterogeneous and asymmetric interactions. This leads to considering a family of controlled Brownian diffusion processes with dynamics depending on the whole collection of marginal probability laws. We prove the well-posedness of such systems and define the control problem together with its related value function. We next prove a law invariance property for the value function which allows us to work on the set of collections of probability laws. We show that the value function satisfies a dynamic programming principle (DPP) on the flow of collections of probability measures. We also derive a chain rule for a class of regular functions along the flows of collections of marginal laws of diffusion processes. Combining the DPP and the chain rule, we prove that the value function is a viscosity solution of a Bellman dynamic programming equation in a $L^2$-set of Wasserstein space-valued functions.

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。

↑