This PhD project will push the boundaries of Continual Reinforcement Learning by investigating how agents can continuously learn and adapt over time, how they can autonomously develop and flexibly apply an ever-expanding repertoire of skills across various tasks, and what representations allow them to do this efficiently. The project aims to create AI systems that can sustain autonomous learning and adaptation in ever-changing environments with limited computational resources. The selected candidate will master and contribute to techniques in deep reinforcement learning, incorporating principles from probabilistic machine learning, such as information theory, intrinsic motivation, and open-ended learning frameworks. The project may use computer games as benchmarking tools or apply findings to robotic systems, including manipulators, intelligent autonomous vehicles, and humanoid robots.