Eich, Yannick ; Alt, Bastian ; Koeppl, Heinz (2024)
Approximate Control for Continuous-Time POMDPs.
International Conference on Artificial Intelligence and Statistics. Valencia, Spain (02.05.2024 - 04.05.2024)
doi: 10.26083/tuprints-00028690
Conference or Workshop Item, Secondary publication, Publisher's Version
Text
eich24a.pdf Copyright Information: CC BY 4.0 International - Creative Commons, Attribution. Download (2MB) |
Item Type: | Conference or Workshop Item |
---|---|
Type of entry: | Secondary publication |
Title: | Approximate Control for Continuous-Time POMDPs |
Language: | English |
Date: | 25 November 2024 |
Place of Publication: | Darmstadt |
Year of primary publication: | 2024 |
Place of primary publication: | Red Hook, NY |
Publisher: | PMLR |
Book Title: | Proceedings of The 27th International Conference on Artificial Intelligence and Statistics |
Series: | Proceedings of Machine Learning Research |
Series Volume: | 238 |
Event Title: | International Conference on Artificial Intelligence and Statistics |
Event Location: | Valencia, Spain |
Event Dates: | 02.05.2024 - 04.05.2024 |
DOI: | 10.26083/tuprints-00028690 |
Corresponding Links: | |
Origin: | Secondary publication service |
Abstract: | This work proposes a decision-making framework for partially observable systems in continuous time with discrete state and action spaces. As optimal decision-making becomes intractable for large state spaces we employ approximation methods for the filtering and the control problem that scale well with an increasing number of states. Specifically, we approximate the high-dimensional filtering distribution by projecting it onto a parametric family of distributions, and integrate it into a control heuristic based on the fully observable system to obtain a scalable policy. We demonstrate the effectiveness of our approach on several partially observed systems, including queueing systems and chemical reaction networks. |
Status: | Publisher's Version |
URN: | urn:nbn:de:tuda-tuprints-286908 |
Classification DDC: | 000 Generalities, computers, information > 004 Computer science 600 Technology, medicine, applied sciences > 621.3 Electrical engineering, electronics |
Divisions: | 18 Department of Electrical Engineering and Information Technology > Institute for Telecommunications > Bioinspired Communication Systems 18 Department of Electrical Engineering and Information Technology > Self-Organizing Systems Lab |
Date Deposited: | 25 Nov 2024 10:47 |
Last Modified: | 26 Nov 2024 15:02 |
URI: | https://tuprints.ulb.tu-darmstadt.de/id/eprint/28690 |
PPN: | 524107661 |
Export: |
View Item |