The NetHack Learning Environment

        Heinrich Küttler+ Nantas Nardelli= Alexander H. Miller+
   Roberta Raileanu* Marco Selvatici# Edward Grefenstette+! Tim Rocktschel+!
       + Facebook AI Research = University of Oxford * New York University
           # Imperial College London ! University College London
                    {hnr,rockt}@fb.com

                       Abstract
     Progress in Reinforcement Learning (RL) algorithms goes hand-in-hand with the
     development of challengi ...