Zhangjie CaoErdem BiyikWoodrow Z. WangAllan RaventosAdrien GaidonGuy RosmanDorsa SadighReinforcement Learning based Control of Imitative Policies for Near-Accident Driving.2020abs/2007.00178CoRRhttps://arxiv.org/abs/2007.00178db/journals/corr/corr2007.html#abs-2007-00178