Reinforcement Learning Across Timescales

This project addresses a fundamental problem faced by many reinforcement learning agents. Commonly used reinforcement learning agents can be seen to have deteriorating performances at increasing frequencies, as they are unable to correctly learn the ordering of expected returns for actions that are applied. We call this the disappearing...

Guidance, Navigation and Control System Design of Envisat Active Debris Removal

Space debris is becoming one of the major risks to be suffered by operating and future space missions. Recent studies show that the number of potentially hazardous uncontrolled orbital bodies is growing with time, increasing the probability of impact with operational satellites. To counteract this problem, several studies are being suggested to...