Real-Time Scheduling via Reinforcement Learning

Robert Glaubius, Terry Tidwell, Christopher Gill, William Smart
Proceedings of the 26th Conference on Uncertainty in Artificial Intelligence, PMLR R8:209-217, 2010.

Abstract

Cyber-physical systems, such as mobile robots, must respond adaptively to dynamic operating conditions. Effective operation of these systems requires that sensing and actuation tasks are performed in a timely manner. Additionally, execution of mission specific tasks such as imaging a room must be balanced against the need to perform more general tasks such as obstacle avoidance. This problem has been addressed by maintaining relative utilization of shared resources among tasks near a user-specified target level. Producing optimal scheduling strategies requires complete prior knowledge of task behavior, which is unlikely to be available in practice. Instead, suitable scheduling strategies must be learned online through interaction with the system. We consider the sample complexity of reinforcement learning in this domain, and demonstrate that while the problem state space is countably infinite, we may leverage the problem’s structure to guarantee efficient learning.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR8-glaubius10a, title = {Real-Time Scheduling via Reinforcement Learning}, author = {Glaubius, Robert and Tidwell, Terry and Gill, Christopher and Smart, William}, booktitle = {Proceedings of the 26th Conference on Uncertainty in Artificial Intelligence}, pages = {209--217}, year = {2010}, editor = {Grünwald, Peter and Spirtes, Peter}, volume = {R8}, series = {Proceedings of Machine Learning Research}, month = {08--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r8/main/assets/glaubius10a/glaubius10a.pdf}, url = {https://proceedings.mlr.press/r8/glaubius10a.html}, abstract = {Cyber-physical systems, such as mobile robots, must respond adaptively to dynamic operating conditions. Effective operation of these systems requires that sensing and actuation tasks are performed in a timely manner. Additionally, execution of mission specific tasks such as imaging a room must be balanced against the need to perform more general tasks such as obstacle avoidance. This problem has been addressed by maintaining relative utilization of shared resources among tasks near a user-specified target level. Producing optimal scheduling strategies requires complete prior knowledge of task behavior, which is unlikely to be available in practice. Instead, suitable scheduling strategies must be learned online through interaction with the system. We consider the sample complexity of reinforcement learning in this domain, and demonstrate that while the problem state space is countably infinite, we may leverage the problem’s structure to guarantee efficient learning.}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T Real-Time Scheduling via Reinforcement Learning %A Robert Glaubius %A Terry Tidwell %A Christopher Gill %A William Smart %B Proceedings of the 26th Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2010 %E Peter Grünwald %E Peter Spirtes %F pmlr-vR8-glaubius10a %I PMLR %P 209--217 %U https://proceedings.mlr.press/r8/glaubius10a.html %V R8 %X Cyber-physical systems, such as mobile robots, must respond adaptively to dynamic operating conditions. Effective operation of these systems requires that sensing and actuation tasks are performed in a timely manner. Additionally, execution of mission specific tasks such as imaging a room must be balanced against the need to perform more general tasks such as obstacle avoidance. This problem has been addressed by maintaining relative utilization of shared resources among tasks near a user-specified target level. Producing optimal scheduling strategies requires complete prior knowledge of task behavior, which is unlikely to be available in practice. Instead, suitable scheduling strategies must be learned online through interaction with the system. We consider the sample complexity of reinforcement learning in this domain, and demonstrate that while the problem state space is countably infinite, we may leverage the problem’s structure to guarantee efficient learning. %Z Reissued by PMLR on 04 October 2026.
APA
Glaubius, R., Tidwell, T., Gill, C. & Smart, W.. (2010). Real-Time Scheduling via Reinforcement Learning. Proceedings of the 26th Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R8:209-217 Available from https://proceedings.mlr.press/r8/glaubius10a.html. Reissued by PMLR on 04 October 2026.

Related Material