Course overview
This course covers an introduction to reinforcement learning, including its mathematical foundations in Markov decision theory, its modern interpretation as a tool for modelling intelligent agents and optimisation, and applications in artificial intelligence.
- Mathematical Foundations
- Tabular Solutions
- Advanced Topics
Course learning outcomes
- Describe modern reinforcement learning and connect it with the underlying mathematical principles
- Demonstrate an understanding of how reinforcement learning is used to solve problems in optimisation and machine learning
- Demonstrate skills in deploying reinforcement learning using computer programming of both traditional and modern techniques
- Apply mathematical techniques to solve a variety of reinforcement learning problems at an appropriate level of difficulty
- Demonstrate skills in communicating about reinforcement learning using mathematics