Academic Journal
A Moreau-Yosida regularization for Markov decision processes
| العنوان: | A Moreau-Yosida regularization for Markov decision processes |
|---|---|
| المؤلفون: | Ortega-Gutiérrez, Israel, Cruz-Suárez, HUGO |
| المصدر: | Proyecciones (Antofagasta, On line); Vol. 40 No. 1 (2021); 117-137 ; Proyecciones. Revista de Matemática; Vol. 40 Núm. 1 (2021); 117-137 ; 0717-6279 ; 10.22199/issn.0717-6279-2021-01 |
| بيانات النشر: | Universidad Católica del Norte. |
| سنة النشر: | 2021 |
| مصطلحات موضوعية: | Discounted Markov decision processes, Uniqueness of optimal policies, Moreau-Yosida regularization, 90C40, 49M20 |
| الوصف: | This paper addresses a class of sequential optimization problems known as Markov decision processes. These kinds of processes are considered on Euclidean state and action spaces with the total expected discounted cost as the objective function. The main goal of the paper is to provide conditions to guarantee an adequate Moreau-Yosida regularization for Markov decision processes (named the original process). In this way, a new Markov decision process that conforms to the Markov control model of the original process except for the cost function induced via the Moreau-Yosida regularization is established. Compared to the original process, this new discounted Markov decision process has richer properties, such as the differentiability of its optimal value function, strictly convexity of the value function, uniqueness of optimal policy, and the optimal value function and the optimal policy of both processes, are the same. To complement the theory presented, an example is provided. |
| نوع الوثيقة: | article in journal/newspaper |
| وصف الملف: | application/pdf |
| اللغة: | English |
| Relation: | https://www.revistaproyecciones.cl/index.php/proyecciones/article/view/4020/3656; https://www.revistaproyecciones.cl/index.php/proyecciones/article/view/4020 |
| DOI: | 10.22199/issn.0717-6279-2021-01-0008 |
| الاتاحة: | https://www.revistaproyecciones.cl/index.php/proyecciones/article/view/4020 https://doi.org/10.22199/issn.0717-6279-2021-01-0008 |
| Rights: | Derechos de autor 2021 Israel Ortega-Gutiérrez, Hugo Cruz-Suárez ; http://creativecommons.org/licenses/by/4.0 |
| رقم الانضمام: | edsbas.A612A76A |
| قاعدة البيانات: | BASE |
| DOI: | 10.22199/issn.0717-6279-2021-01-0008 |
|---|