SDSC4001 - Foundation of Reinforcement Learning | ||||||||||
| ||||||||||
* The offering term is subject to change without prior notice | ||||||||||
Course Aims | ||||||||||
This advanced elective course introduces the essential elements and mathematical foundations of the modern reinforcement learning: the optimal control theory, including dynamic programming and numerical techniques. It emphasizes both the fundamental theories in control theory and the numerical methods in context of reinforcement learning algorithms. It also equips students with computing algorithms and techniques for applications to some practical problems. | ||||||||||
Assessment (Indicative only, please check the detailed course information) | ||||||||||
Continuous Assessment: 40% | ||||||||||
Examination: 60% | ||||||||||
Examination Duration: 3 hours | ||||||||||
Detailed Course Information | ||||||||||
SDSC4001.pdf | ||||||||||
Useful Links | ||||||||||
School of Data Science |