Deep reinforcement learning algorithms, and in particular meta reinforcement learning algorithms have the potential to solve a variety of complex robotic tasks in unstructured environments. But these algorithms have typically been limited to simulation or extremely simple lab environments, largely because providing supervision effectively to these algorithms is very challenging. In this talk, I will discuss some of the issues that come with supervision in meta reinforcement learning and discuss some recent work which aims to tackle this issue.

Abhishek Gupta is a third year Ph.D student at UC Berkeley, working with Professor Sergey Levine and Professor Pieter Abbeel. Abhishek's research interests focus on Deep Reinforcement Learning in robotics, with an emphasis on multi-task learning, transfer learning, imitation learning and dexterous manipulation. Abhishek received a B.S in Electrical Engineering and Computer Science from UC Berkeley working with Professor Pieter Abbeel on apprenticeship learning and hierarchical planning. Abhishek is the recipient of the NSF graduate research fellowship as well as the NDSEG graduate fellowship.