Linear programming for finite-horizon vector-valued Markov decision processes
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910975663276032 |
|---|---|
| author | Mifrani, Anas Noll, Dominikus |
| author_facet | Mifrani, Anas Noll, Dominikus |
| contents | We propose a vector linear programming formulation for a non-stationary, finite-horizon Markov decision process with vector-valued rewards. Pareto efficient policies are shown to correspond to efficient solutions of the linear program, and vector linear programming theory allows us to fully characterize deterministic efficient policies. An algorithm for enumerating all efficient deterministic policies is presented then tested numerically in an engineering application. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_13697 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Linear programming for finite-horizon vector-valued Markov decision processes Mifrani, Anas Noll, Dominikus Optimization and Control 90C40, 90C29, 90C05 We propose a vector linear programming formulation for a non-stationary, finite-horizon Markov decision process with vector-valued rewards. Pareto efficient policies are shown to correspond to efficient solutions of the linear program, and vector linear programming theory allows us to fully characterize deterministic efficient policies. An algorithm for enumerating all efficient deterministic policies is presented then tested numerically in an engineering application. |
| title | Linear programming for finite-horizon vector-valued Markov decision processes |
| topic | Optimization and Control 90C40, 90C29, 90C05 |
| url | https://arxiv.org/abs/2502.13697 |