A dynamical neural network approach for distributionally robust chance constrained Markov decision process
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| 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 |