Learning to steer with Brownian noise
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913530837467136 |
|---|---|
| author | Ankirchner, Stefan Christensen, Sören Kallsen, Jan Borne, Philip Le Perko, Stefan |
| author_facet | Ankirchner, Stefan Christensen, Sören Kallsen, Jan Borne, Philip Le Perko, Stefan |
| contents | This paper considers an ergodic version of the bounded velocity follower problem, assuming that the decision maker lacks knowledge of the underlying system parameters and must learn them while simultaneously controlling. We propose algorithms based on moving empirical averages and develop a framework for integrating statistical methods with stochastic control theory. Our primary result is a logarithmic expected regret rate. To achieve this, we conduct a rigorous analysis of the ergodic convergence rates of the underlying processes and the risks of the considered estimators. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_03221 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Learning to steer with Brownian noise Ankirchner, Stefan Christensen, Sören Kallsen, Jan Borne, Philip Le Perko, Stefan Machine Learning Probability Statistics Theory 93E10, 60G35, 68Q32, 93C73, 93E11 This paper considers an ergodic version of the bounded velocity follower problem, assuming that the decision maker lacks knowledge of the underlying system parameters and must learn them while simultaneously controlling. We propose algorithms based on moving empirical averages and develop a framework for integrating statistical methods with stochastic control theory. Our primary result is a logarithmic expected regret rate. To achieve this, we conduct a rigorous analysis of the ergodic convergence rates of the underlying processes and the risks of the considered estimators. |
| title | Learning to steer with Brownian noise |
| topic | Machine Learning Probability Statistics Theory 93E10, 60G35, 68Q32, 93C73, 93E11 |
| url | https://arxiv.org/abs/2410.03221 |