Learning Robust Multi-Modal Polices for Industrial Robotic Tasks via Reinforcement Learning and Demonstrations


Jianlan Luo*, Oleg Sushkov*, Rugile Pevceviciute*, Wenzhao Lian

Chang Su, Mel Vecerik, Ning Ye, Stefan Schaal, Jon Scholz

Google [X]

Google Deepmind

*Equal contribution


RSS 2021

Paper Code Dataset