The use of robots in society could be expanded by using reinforcement learning (RL) to allow robots to learn and adapt to new situations on-line. RL is a paradigm for learning sequential decision making tasks, usually formulated as a Markov Decision Process (MDP). For an RL algorithm to be practical for robotic control tasks, it must learn in very few samples, while continually taking actions in real-time. In addition, the algorithm must learn efficiently in the face of noise, sensor/actuator delays, and continuous state features.
Securing critical networked cyber-physical systems (NCPSs) such as the power grid or transportation systems has emerged as a major national and global priority. The networked nature of such systems renders them vulnerable to a range of attacks both in cyber and physical domains as corroborated by recent threats such as the Stuxnet virus.
