MIT 6. S191 (2020): Generalizable Autonomy for Robot Manipulation

MIT Introduction to Deep Learning 6. S191: Lecture 8 Generalizable Autonomy for Robot Manipulation Lecturer: Animesh Garg (NVIDIA University of Toronto) January 2020 For all lectures, slides, and lab materials: Lecture Outline 0:00 Introduction 3:45 Achieving generalizable autonomy 4:19 Leveraging imitation learning 6:08 Learning visuomotor policies 13:09 Learning skills 16:38 Offpolicy RL + ACTeach 22:02 Compositional planning 27:20 Modelbased RL 34:37 Leveraging task structure 36:35 Neural task programming (NTP) 43:04 Data for robotics 44:24 RoboTurk 45:54 Summary Subscribe to stay up to date with new deep learning lectures at MIT, or follow us MITDeepLearning on Twitter and Instagram to stay fullyconnected