On Supervised Online Rolling-Horizon Control for Infinite-Horizon Discounted Markov Decision Processes
IEEE Transactions on Automatic Control · 2024-02 · 69 (2) · 1060-1065
DOI: 10.1109/tac.2023.3274791 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Automatic Control, 2024-02. Verfasst von Hyeong Soo Chang. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 14 Literaturangaben.
Abstract (Originalsprache)
This note revisits the rolling-horizon control approach to the problem of Markov decision process (MDP) with infinite-horizon discounted expected reward criterion. Distinguished from the classical value-iteration approaches, we develop an asynchronous online algorithm based on policy iteration integrated with a multipolicy improvement method of policy switching. A sequence of monotonically improving solutions to the forecast-horizon sub-MDP is generated by updating the current solution only at the currently visited state, building in effect a rolling-horizon control policy for the MDP over infinite horizon. Feedbacks from “supervisors,” if available, can be also incorporated while updating. We focus on the convergence issue with a relation to the transition structure of the MDP. Either a global convergence to an optimal forecast-horizon policy or a local convergence to a “locally-optimal” fixed-policy in a finite time is achieved by the algorithm depending on the structure.
Zitieren
APA
Chang, H. S. (2024). On Supervised Online Rolling-Horizon Control for Infinite-Horizon Discounted Markov Decision Processes. IEEE Transactions on Automatic Control, 69(2), 1060-1065. https://doi.org/10.1109/tac.2023.3274791
Vancouver
Chang HS. On Supervised Online Rolling-Horizon Control for Infinite-Horizon Discounted Markov Decision Processes. IEEE Transactions on Automatic Control. 2024;69(2):1060-1065. doi:10.1109/tac.2023.3274791
BibTeX
@article{Chang2024,
author = {Chang, Hyeong Soo},
title = {On Supervised Online Rolling-Horizon Control for Infinite-Horizon Discounted Markov Decision Processes},
journal = {IEEE Transactions on Automatic Control},
year = {2024},
volume = {69},
number = {2},
pages = {1060--1065},
doi = {10.1109/tac.2023.3274791}
}
EUVIMED