The Challenges of Reinforcement Learning in Robotics and Optimal Control

Reinforcement Learning (RL) is an emerging technology for designing control systems that find optimal policy, through simulated or actual experience, according to a performance measure given by the designer. This paper discusses a widely used RL algorithm called Q-learning. This paper discuss how to apply these algorithms to robotics and optimal control systems, where several key challenges must be addressed for it to be useful. We discuss how Q-learning algorithm can adapted to work in continuous states and action spaces, the methods for computing rewards which generates an adaptive optimal controller and accelerate learning process and finally the safe exploration approaches.