Reconciling λ-Returns with Experience Replay

          Brett Daley                 Christopher Amato
    Khoury College of Computer Sciences       Khoury College of Computer Sciences
       Northeastern University             Northeastern University
        Boston, MA 02115                 Boston, MA 02115
     b.daley@northeastern.edu             c.amato@northeastern.edu

                       Abstract
     Modern deep reinforcement learning methods have departed from the incremental
     lea ...