Approximate Information States for Worst-Case Control and Learning in Uncertain Systems
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910529811906560 |
|---|---|
| author | Dave, Aditya Venkatesh, Nishanth Malikopoulos, Andreas A. |
| author_facet | Dave, Aditya Venkatesh, Nishanth Malikopoulos, Andreas A. |
| contents | In this paper, we investigate discrete-time decision-making problems in uncertain systems with partially observed states. We consider a non-stochastic model, where uncontrolled disturbances acting on the system take values in bounded sets with unknown distributions. We present a general framework for decision-making in such problems by using the notion of the information state and approximate information state, and introduce conditions to identify an uncertain variable that can be used to compute an optimal strategy through a dynamic program (DP). Next, we relax these conditions and define approximate information states that can be learned from output data without knowledge of system dynamics. We use approximate information states to formulate a DP that yields a strategy with a bounded performance loss. Finally, we illustrate the application of our results in control and reinforcement learning using numerical examples. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2301_05089 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Approximate Information States for Worst-Case Control and Learning in Uncertain Systems Dave, Aditya Venkatesh, Nishanth Malikopoulos, Andreas A. Systems and Control Artificial Intelligence Optimization and Control In this paper, we investigate discrete-time decision-making problems in uncertain systems with partially observed states. We consider a non-stochastic model, where uncontrolled disturbances acting on the system take values in bounded sets with unknown distributions. We present a general framework for decision-making in such problems by using the notion of the information state and approximate information state, and introduce conditions to identify an uncertain variable that can be used to compute an optimal strategy through a dynamic program (DP). Next, we relax these conditions and define approximate information states that can be learned from output data without knowledge of system dynamics. We use approximate information states to formulate a DP that yields a strategy with a bounded performance loss. Finally, we illustrate the application of our results in control and reinforcement learning using numerical examples. |
| title | Approximate Information States for Worst-Case Control and Learning in Uncertain Systems |
| topic | Systems and Control Artificial Intelligence Optimization and Control |
| url | https://arxiv.org/abs/2301.05089 |