A dynamical neural network approach for distributionally robust chance-constrained Markov decision process  

作　　者：Tian Xia Jia Liu Zhiping Chen 

机构地区：[1]School of Mathematics and Statistics,Xi’an Jiaotong University,Xi’an,710049,China

出　　处：《Science China Mathematics》2024年第6期1395-1418,共24页中国科学（数学）（英文版）

基　　金：supported by National Natural Science Foundation of China(Grant Nos.11991023 and 12371324);National Key R&D Program of China(Grant No.2022YFA1004000)。

摘　　要：In this paper,we study the distributionally robust joint chance-constrained Markov decision process.Utilizing the logarithmic transformation technique,we derive its deterministic reformulation with bi-convex terms under the moment-based uncertainty set.To cope with the non-convexity and improve the robustness of the solution,we propose a dynamical neural network approach to solve the reformulated optimization problem.Numerical results on a machine replacement problem demonstrate the efficiency of the proposed dynamical neural network approach when compared with the sequential convex approximation approach.

关 键 词：Markov decision process chance constraints distributionally robust optimization moment-based ambiguity set dynamical neural network 

分 类 号：O211.62[理学—概率论与数理统计] TP183[理学—数学]