Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes

Reinforcement learning (RL), particularly its combination with deep neural networks referred to as deep RL (DRL), has shown tremendous promise across a wide range of applications, suggesting its potential for enabling the development of sophisticated robotic behaviors. Robotics problems, however, pose fundamental difficulties for the application of RL, stemming from the complexity and cost of interacting with the physical world. These challenges notwithstanding, recent advances have enabled DRL to succeed at some real-world robotic tasks. However, state-of-the-art DRL solutions’ maturity varies significantly across robotic applications. In this talk, I will review the current progress of DRL in real-world…

• NS
  National Science Foundation

  Award: 2019844
• UO
  University of Texas at Austin

  Awards: E2061621, N00014-18-2243, NRT-2125858, FAIN-2019844
• OO
  Office of Naval Research

  Awards: N00014-18-2243, N00014
• AR
  Army Research Office

  Award: E2061621