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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xia, Tian, Liu, Jia, Chen, Zhiping
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911745336934400
author Xia, Tian
Liu, Jia
Chen, Zhiping
author_facet Xia, Tian
Liu, Jia
Chen, Zhiping
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2312_15312
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle A dynamical neural network approach for distributionally robust chance constrained Markov decision process
Xia, Tian
Liu, Jia
Chen, Zhiping
Optimization and Control
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.
title A dynamical neural network approach for distributionally robust chance constrained Markov decision process
topic Optimization and Control
url https://arxiv.org/abs/2312.15312