Title :
Reinforcement Learning for Routing in Ad Hoc Networks
Author_Institution :
Dept. of Comput. Sci., Univ. of Helsinki, Helsinki
Abstract :
We show how routing in ad hoc networks can be modeled as a sequential decision making problem with incomplete information. More precisely, we show how to map routing into a reinforcement learning problem involving a partially observable Markov decision process, and present an algorithm for optimizing the performance of the nodes in this model. We also present simulation results with our model.
Keywords :
ad hoc networks; learning (artificial intelligence); telecommunication computing; telecommunication network routing; Markov decision process; ad hoc networks routing; reinforcement learning; sequential decision making problem; Ad hoc networks; Communication networks; Costs; Function approximation; Game theory; Learning; Parameter estimation; Routing; Stochastic processes; Uncertainty;
Conference_Titel :
Modeling and Optimization in Mobile, Ad Hoc and Wireless Networks and Workshops, 2007. WiOpt 2007. 5th International Symposium on
Conference_Location :
Limassol
Print_ISBN :
978-1-4244-0960-0
Electronic_ISBN :
978-1-4244-0961-7
DOI :
10.1109/WIOPT.2007.4480049
