Gaussian Processes for Data-Efficient Learning in Robotics and Control

Autonomous learning has been a promising direction in control and robotics for more than a decade since data-driven learning allows to reduce the amount of engineering knowledge, which is otherwise required. However, autonomous reinforcement learning (RL) approaches typically require many interactions with the system to learn controllers, which is a practical limitation in real systems, such as robots, where many interactions can be impractical and time consuming. To address this problem, current learning approaches typically require task-specific knowledge in form of expert demonstrations, realistic simulators, pre-shaped policies, or specific knowledge about the underlying dynamics. In this paper, we follow…

• IC
  Imperial College London
• MU
  Multidisciplinary University Research Initiative
• EA
  Engineering and Physical Sciences Research Council

  Award: EP/J012300/1
• OO
  Office of Naval Research

  Awards: N00014-09-1-1052, N00014