Kagan Tumer's Publications

Display Publications by [Year] [Type] [Topic]


Multiagent Reinforcement Learning in a Distributed Sensor Network with Indirect Feedback. M. Colby and K. Tumer. In Proceedings of the Twelveth International Joint Conference on Autonomous Agents and Multiagent Systems, pp. 941–948, Minneapolis, MN, May 2013.

Abstract

Highly accurate sensor measurements are crucial in order for power plants to effectively operate, as well as to predict and subsequently prevent any potentially catastrophic failures. As the cost of sensors decreases while their power increases, distributed sensor networks become a more attractive option for implementation in power plants. In this work, we investigate the use of a distributed sensor network to achieve highly accurate measurements. We apply shaped rewards to local components and use a simple learning algorithm at each sensor in order to maximize those rewards. Our results show that the measurements from a sensor network trained using shaped rewards are up to two orders of magnitude more accurate than a sensor network trained with a traditional global reward. Further, the algorithm proposed scales well to large networks, and is robust to measurement noise and sensor failures.

Download

[PDF]422.9kB  

BibTeX Entry

@inproceedings{tumer-colby_aamas13,
        author = {M. Colby and  K. Tumer},
        title = {Multiagent Reinforcement Learning in a Distributed Sensor Network with Indirect Feedback},
        booktitle = {Proceedings of the Twelveth International Joint Conference on Autonomous Agents and Multiagent Systems},
	month = {May},
          pages ={941-948},
	address = {Minneapolis, MN},
	abstract={Highly accurate sensor measurements are crucial in order for power plants to effectively operate, as well as to predict and subsequently prevent any potentially catastrophic failures.  As the cost of sensors decreases while their power increases, distributed sensor networks become a more attractive option for implementation in power plants.  In this work, we investigate the use of a distributed sensor network to achieve highly accurate measurements. We apply shaped rewards to local components and use a simple learning algorithm at each sensor in order to maximize those rewards. Our results show that the measurements from a sensor network trained using shaped rewards are up to two orders of magnitude more accurate than a sensor network trained with a traditional global reward.  Further, the algorithm proposed scales well to large networks, and is robust to measurement noise and sensor failures.},
	bib2html_pubtype = {Refereed Conference Papers},
	bib2html_rescat = {Reinforcement Learning, Multiagent Systems},
        year = {2013}
}

Generated by bib2html.pl (written by Patrick Riley ) on Tue Jun 26, 2018 19:10:42