arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1609.02697math.PRmath.OC
收藏

部分观测控制问题的Wasserstein空间中的随机滤波和Bellman方程

Randomized filtering and Bellman equation in Wasserstein space for partial observation control problem

Elena Bandini, Andrea Cosso, Marco Fuhrman, Huyên Pham

摘要:

研究了部分可观测扩散的随机最优控制问题。利用文献[4]中的控制随机化方法,证明了一个相应的值函数的随机化动态规划原理(DPP),该值函数是由相关过滤过程的流性质得到的。这个DPP是我们的主要结果的关键一步:部分观测控制问题的值函数作为唯一的黏性解,相应的动态规划Hamilton-Jacobi-Bellman(HJB)方程的特征。后者被表述为一个新的,完全非线性偏微分方程的Wasserstein空间的概率测度。我们的方法的一个重要特点是,它不需要任何非退化条件的扩散系数,并没有施加任何条件,以保证存在的密度的过滤过程解决方案的控制Zakai方程,通常做的分离问题。最后,在部分可观测的非高斯线性二次模型的情况下,给出了HJB方程的显式解。

英文摘要:

We study a stochastic optimal control problem for a partially observed diffusion. By using the control randomization method in [4], we prove a corresponding randomized dynamic programming principle (DPP) for the value function, which is obtained from a flow property of an associated filter process. This DPP is the key step towards our main result: a characterization of the value function of the partial observation control problem as the unique viscosity solution to the corresponding dynamic programming Hamilton-Jacobi-Bellman (HJB) equation. The latter is formulated as a new, fully non linear partial differential equation on the Wasserstein space of probability measures. An important feature of our approach is that it does not require any non-degeneracy condition on the diffusion coefficient, and no condition is imposed to guarantee existence of a density for the filter process solution to the controlled Zakai equation, as usually done for the separated problem. Finally, we give an explicit solution to our HJB equation in the case of a partially observed non Gaussian linear quadratic model.

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。

↑