TU Darmstadt / ULB / TUprints

Approximate Control for Continuous-Time POMDPs

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

[img] 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:
Actions (login required)
View Item View Item