A Reinforcement Learning Approach to Age of Information in Multi-User Networks

Creative Commons License

Ceran E. T., Gunduz D., Gyorgy A.

29th IEEE Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC), Bologna, Italy, 9 - 12 September 2018, pp.1967-1971 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.1109/pimrc.2018.8580701
  • City: Bologna
  • Country: Italy
  • Page Numbers: pp.1967-1971
  • Middle East Technical University Affiliated: No


Scheduling the transmission of time-sensitive data to multiple users over error-prone communication channels is studied with the goal of minimizing the long-term average age of information (AoI) at the users under a constraint on the average number of transmissions. The source can transmit only to a single user at each time slot, and after each transmission, it receives an instantaneous ACK/NACK feedback from the intended receiver, and decides on when and to which user to transmit the next update. The optimal scheduling policy is first studied under different feedback mechanisms when the channel statistics are known; in particular, the standard automatic repeat request (ARQ) and hybrid ARQ (HARQ) protocols are considered. Then a reinforcement learning (RL) approach is introduced, which does not assume any a priori information on the random processes governing the channel states. Different RL methods are applied and compared through numerical simulations.