SDSC6007 - Dynamic Programming and Reinforcement Learning

Offering Academic Unit
School of Data Science
Credit Units
Course Duration
One Semester
Course Offering Term*:
Semester B 2021/22

* The offering term is subject to change without prior notice
Course Aims

The course introduces Dynamic Programming - the basic models and solution techniques for problems of sequential decision making under uncertainty, and Reinforcement Learning - a framework for learning through an autonomous agent’s trial and error interaction with the world to make near optimal decisions. 

The course will cover the following foundational materials related to dynamic programming and reinforcement learning, including Markov decision processes, value functions, Monte Carlo estimation, dynamic programming, temporal difference learning and function approximation. The objective of this course is to help students develop intuitive understandings of these advanced optimization and learning methods and algorithms, familiarize with the mathematical theories of these methods and algorithms, and be able to apply Dynamic Programming and Reinforcement Learning techniques to solve real-world problems.

Assessment (Indicative only, please check the detailed course information)

Continuous Assessment: 100%
Detailed Course Information


Useful Links

School of Data Science