带双因果约束的多周期控制问题的动态规划原理
A dynamic programming principle for multiperiod control problems with bicausal constraints
AI总结:
针对带非参数不确定性的多周期随机控制问题,提出适配$(p, \infty)$--Wasserstein距离$\mathcal{AW}_p^\infty$,证明其可保障控制问题连续性,且对应分布鲁棒优化问题可通过动态规划求解,还推导了半可分代价下的极小极大定理与一阶灵敏度结果。
摘要:
我们研究基础概率模型存在非参数不确定性的多周期随机控制问题。我们在概率测度空间上推导了一种新度量,称为适配的$(p, \infty)$--Wasserstein距离$\mathcal{AW}_p^\infty$,它具备以下性质:(1)该距离生成的拓扑可保证随机控制问题的连续性;(2)对应的$\mathcal{AW}_p^\infty$-分布鲁棒优化(DRO)问题可通过包含单步Wasserstein-DRO问题的动态规划原理求解。若代价函数是半可分的,我们进一步证明即使$\mathcal{AW}_p^\infty$对应的球通常既不凸也不紧,极小极大定理依然成立。我们还推导了一阶灵敏度结果。
英文摘要:
We consider multiperiod stochastic control problems with non-parametric uncertainty on the underlying probabilistic model. We derive a new metric on the space of probability measures, called the adapted $(p, \infty)$--Wasserstein distance $\mathcal{AW}_p^\infty$ with the following properties: (1) the adapted $(p, \infty)$--Wasserstein distance generates a topology that guarantees continuity of stochastic control problems and (2) the corresponding $\mathcal{AW}_p^\infty$-distributionally robust optimization (DRO) problem can be computed via a dynamic programming principle involving one-step Wasserstein-DRO problems. If the cost function is semi-separable, then we further show that a minimax theorem holds, even though balls with respect to $\mathcal{AW}_p^\infty$ are neither convex nor compact in general. We also derive first-order sensitivity results.
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。