Mutual Information Optimal Density Control of Linear Systems and Generalized Schrödinger Bridges with Reference Refinement
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_ | 1866914548926119936 |
|---|---|
| author | Enami, Shoju Kashima, Kenji |
| author_facet | Enami, Shoju Kashima, Kenji |
| contents | We consider a mutual information (MI) regularized version of optimal density control of a discrete-time linear system. MI optimal control has been proposed as an extension of maximum entropy optimal control to trade off between control performance and benefits provided by stochastic inputs. MI regularization induces stochasticity in the policy, which poses challenges for applications of MI optimal control in safety-critical scenarios. To remedy this situation, we impose Gaussian density constraints at specified times to directly control state uncertainty. For this MI optimal density control problem, we propose an alternating optimization algorithm and derive the closed form of each step in the algorithm. In addition, we reveal that the alternating optimization of the MI optimal density control problem coincides with that of the so-called generalized Schrödinger bridge problem associated with the discrete-time linear system. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_09349 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Mutual Information Optimal Density Control of Linear Systems and Generalized Schrödinger Bridges with Reference Refinement Enami, Shoju Kashima, Kenji Optimization and Control Machine Learning Systems and Control We consider a mutual information (MI) regularized version of optimal density control of a discrete-time linear system. MI optimal control has been proposed as an extension of maximum entropy optimal control to trade off between control performance and benefits provided by stochastic inputs. MI regularization induces stochasticity in the policy, which poses challenges for applications of MI optimal control in safety-critical scenarios. To remedy this situation, we impose Gaussian density constraints at specified times to directly control state uncertainty. For this MI optimal density control problem, we propose an alternating optimization algorithm and derive the closed form of each step in the algorithm. In addition, we reveal that the alternating optimization of the MI optimal density control problem coincides with that of the so-called generalized Schrödinger bridge problem associated with the discrete-time linear system. |
| title | Mutual Information Optimal Density Control of Linear Systems and Generalized Schrödinger Bridges with Reference Refinement |
| topic | Optimization and Control Machine Learning Systems and Control |
| url | https://arxiv.org/abs/2605.09349 |