Published or accepted to be published in journals covered by SCI, SSCI or AHCI

  • A.Demir.
    (2023) Learning what to memorize: Using intrinsic motivation to form useful memory in partially observable reinforcement learning.
  • A.Demir , E.Çilden and F.Polat.
    (2022) Landmark based guidance for reinforcement learning agents under partial observability.
    International Journal Of Machine Learning And Cybernetics ,
  • A.Demir , E.Çilden and F.Polat.
    (2019) Automatic landmark discovery for learning agents under partial observability.
    The Knowledge Engineering Review , Vol. 34,
  • A.Demir , E.Çilden and F.Polat.
    (2019) Generating Effective Initiation Sets for Subgoal-Driven Options.
    Advances In Complex Systems , Vol. 22,