Robotics, control

Enable robots and other agents to develop broadly intelligent behavior through learning and interaction. Exploring the intersection of machine learning and robotic control, including

• end-to-end learning of visual perception and robotic manipulation skills,
• deep reinforcement learning of general skills from autonomously collected experience,
• imitation learning,
• learning from various sources of human feedback,
• learning from interaction with other agents,
• meta-learning algorithms that can enable fast learning of new concepts and behaviors.