Hyperparameter Selection for Imitation Learning

  Leonard Hussenot * 1 2 Marcin Andrychowicz * 1 Damien Vincent * 1 Robert Dadashi 1 Anton Raichuk 1
  Lukasz Stafiniak 1 Sertan Girgin 1 Raphael Marinier 1 Nikola Momchev 1 Sabela Ramos 1 Manu Orsini 1
               Olivier Bachem 1 Matthieu Geist 1 Olivier Pietquin 1

             Abstract                 the expert implements an optimal policy according to an
                                  unknown reward function. This approach, also known ...