题目：带有贝叶斯模糊集的可调节分布鲁棒最优控制问题

演讲人：陈志平教授，西安交通大学

主持人：林贵华教授，上海大学管理学院

时间：2026年6月26日（周五），上午10:00

地点：上海大学校本部东区1号楼管理学院420会议室

主办单位：上海大学管理学院、上海大学管理学院青年教师联谊会

演讲人简介：

知名优化专家，国家天元数学西北中心副主任，西安交通大学二级教授；长期从事随机规划、强化学习、金融风险度量、保险精算与投资分析等领域的学术研究，代表性论文发表在SIOPT, MOR, MP, EJOR, JBF等顶级期刊；主持国家重点研发计划重点专项、国家自然科学基金项目及横向项目20余项；担任OR Spectrum、Big Data and Information Analytics、西安交通大学学报等期刊编委；现任中国运筹学会常务理事，中国优选法统筹法与经济数学研究会量化金融与保险分会常务理事，中国管理科学与工程学会金融计量与风险管理研究会理事，中国工业与应用学学会竞赛工作委员会委员等。

演讲内容简介：

In stochastic optimal control (SOC), uncertainty may arise from incomplete knowledge of true probability distribution of underlying environment, which is known as Knightian or epistemic uncertainty. Distributionally robust optimal control (DROC) models are subsequently proposed to tackle this uncertainty. While such models are effective in some practical applications, most existing DROC models are offline and can be overly conservative when data are scarce. Moreover, they cannot be applied to the case when samples are generated episodically. We propose an adaptive DROC model in which the ambiguity set is updated via Bayesian learning from new data. Under some moderate conditions, we derive a tractable risk-averse reformulation and establish consistency of the optimal value function and optimal policy for an infinite-horizon SOC. We also study the stability and statistical robustness of the proposed model with respect to sample perturbations that often arise in data-driven environments. To solve the episodic Bayesian DROC model, we propose a Bellman-operator cutting-plane algorithm that is computationally efficient and provably convergent. Numerical results on an inventory control problem demonstrate the effectiveness, adaptivity, and robust performance of the proposed model and algorithm.

欢迎广大师生参加！