Advanced Artificial Intelligence and Machine Learning: Reinforcement Learning and Robotics

Discover the algorithms powering the next generation of intelligent machines in this intensive three-week journey through reinforcement learning, from the mathematical foundations of decision-making to advanced AI agents and autonomous robotics.

You will build a strong foundation in reinforcement learning, progressing from Markov Decision Processes and Q-learning to deep Q-networks, policy gradients, and advanced optimisation algorithms such as PPO. You will then explore continuous control, advanced RL algorithms and robot learning, alongside simulation-to-reality transfer, exploration strategies, and the challenges of designing effective reward functions. In the final part of the course you will discover cutting-edge applications of reinforcement learning, including robot foundation models, imitation learning, offline RL, AI alignment, and multi-agent systems, before exploring emerging research frontiers and generalist agents.

Combining theoretical foundations, algorithmic understanding and practical case studies, the course equips students with a broad understanding of modern reinforcement learning, its real-world applications and limitations, and the open research challenges shaping its future. It is ideal for students with an interest in AI, machine learning, robotics or computer science who want to move beyond the fundamentals and explore the algorithms, applications, and research frontiers shaping the future of intelligent autonomous systems.