Main papers:
Deep Predictive Policy Training using Reinforcement Learning Ali Ghadirzadeh, Atsuto Maki, Danica Kragic, Mårten Björkman https://arxiv.org/abs/1703.00727
Sim-to-Real Robot Learning from Pixels with Progressive Nets: Andrei A. Rusu, Matej Vecerik, Thomas Rothorl, Nicolas Heess, Razvan Pascanu, Raia Hadsell https://arxiv.org/abs/1610.04286
Bonus Papers:
Unsupervised Perceptual Rewards for Imitation Learning Pierre Sermanet, Kelvin Xu, Sergey Levine
https://arxiv.org/abs/1612.06699
Incorporating Human Domain Knowledge into Large Scale Cost Function Learning: Markus Wulfmeier, Dushyant Rao, Ingmar Posner