Relaxed Control with Entropy Regularization for Itô Stochastic Systems with Input Delay
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911736472272896 |
|---|---|
| author | Li, Ruixue Li, Xun Zhang, Zhaorong Xu, Juanjuan |
| author_facet | Li, Ruixue Li, Xun Zhang, Zhaorong Xu, Juanjuan |
| contents | This paper investigates the infinite-horizon classical stochastic optimal control problem with input delay under an entropy-regularized relaxed control framework. In particular, by constructing a relaxed system and introducing an entropy regularization term, we reformulate the classical optimal control problem into an entropy regularized formulation, and derive the optimal controller that follows a Gaussian distribution. Furthermore, we show that the optimal Gaussian control distribution converges to the optimal Dirac measure as the exploration weight tends to zero. Numerical simulation is provided to validate the effectiveness of the proposed method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2606_01058 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Relaxed Control with Entropy Regularization for Itô Stochastic Systems with Input Delay Li, Ruixue Li, Xun Zhang, Zhaorong Xu, Juanjuan Optimization and Control 93-08 This paper investigates the infinite-horizon classical stochastic optimal control problem with input delay under an entropy-regularized relaxed control framework. In particular, by constructing a relaxed system and introducing an entropy regularization term, we reformulate the classical optimal control problem into an entropy regularized formulation, and derive the optimal controller that follows a Gaussian distribution. Furthermore, we show that the optimal Gaussian control distribution converges to the optimal Dirac measure as the exploration weight tends to zero. Numerical simulation is provided to validate the effectiveness of the proposed method. |
| title | Relaxed Control with Entropy Regularization for Itô Stochastic Systems with Input Delay |
| topic | Optimization and Control 93-08 |
| url | https://arxiv.org/abs/2606.01058 |