Continuous Coordination As a Realistic Scenario for Lifelong Learning

       Hadi Nekoei * 1 Akilesh Badrinaaraayanan * 1 2 Aaron Courville 1 2 3 Sarath Chandar 1 4 3

             Abstract                 1. Introduction
                                  Deep reinforcement learning (RL) has shown an immense
                                  potential to achieve superhuman performance (Mnih et al.,
   Current deep reinforcement learning (RL) algo-        2013; Silver et al., 2018) on some narro ...