Reinforcement Learning based Control of Imitative Policies for Near-Accident Driving
Published in Robotics: Science and Systems (RSS), 2020
Recommended citation: Z. Cao*, E. Biyik*, W. Wang, A. Raventos, A. Gaidon, G. Rosman, D. Sadigh. Reinforcement Learning based Control of Imitative Policies for Near-Accident Driving. Robotics: Science and Systems (RSS), July 2020.
Collaborated with Toyota Research Institute to design policies to safely and efficiently control vehicles in near- accident scenarios using a novel hierarchical reinforcement learning over imitation learning model.