SDSC8006 - Reinforcement Learning | ||||||||
| ||||||||
| * The offering term is subject to change without prior notice | ||||||||
Course Aims | ||||||||
The goal of this course is to provide a clear account of the key concepts and solution algorithms of reinforcement learning. Topics include optimal control, dynamic programming (including policy iteration and value iteration), Markov decision processes, temporal-difference learning, value approximation, policy approximation, Q-learning and various reinforcement learning algorithms. Emphasis will be placed on trade-off between exploitation and exploration, and the trade-off between the sub-optimality and tractability. We will learn how to formulate, analyze and solve various reinforcement learning problems. Applications in various fields will be also discussed. | ||||||||
Assessment (Indicative only, please check the detailed course information) | ||||||||
Continuous Assessment: 70% | ||||||||
Examination: 30% | ||||||||
Examination Duration: 2 hours | ||||||||
Detailed Course Information | ||||||||
| SDSC8006.pdf | ||||||||
Useful Links | ||||||||
| School of Data Science | ||||||||
