5th International ICST Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks

Research Article

Reinforcement Learning for Routing in Ad Hoc Networks

  • @INPROCEEDINGS{10.1109/WIOPT.2007.4480049,
        author={Petteri Nurmi},
        title={Reinforcement Learning for Routing in Ad Hoc Networks},
        proceedings={5th International ICST Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks},
        publisher={IEEE},
        proceedings_a={WIOPT},
        year={2008},
        month={3},
        keywords={Ad hoc networks  Communication networks  Costs  Function approximation  Game theory  Learning  Parameter estimation  Routing  Stochastic processes  Uncertainty},
        doi={10.1109/WIOPT.2007.4480049}
    }
    
  • Petteri Nurmi
    Year: 2008
    Reinforcement Learning for Routing in Ad Hoc Networks
    WIOPT
    IEEE
    DOI: 10.1109/WIOPT.2007.4480049
Petteri Nurmi1,*
  • 1: Helsinki Institute for Information Technology HIIT Department of Computer Science, P.O. Box 68, FI-00014 University of Helsinki, Finland
*Contact email: petteri.nurmi@cs.helsinki.fi

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