CM52048: Reinforcement learning
[Page last updated: 22 April 2025]
| Academic Year: | 2025/26 |
| Owning Department/School: | Department of Computer Science |
| Credits: | 10 [equivalent to 20 CATS credits] |
| Notional Study Hours: | 200 |
| Level: | Masters UG & PG (FHEQ level 7) |
| Period: |
|
| Assessment Summary: | CWPG 100% |
| Assessment Detail: |
|
| Supplementary Assessment: |
|
| Requisites: |
In taking this module you cannot take CM32032 OR take CM30359
Before taking this module you must take CM22009 OR take CM20315 |
| Learning Outcomes: |
On completion of the unit, the students will be able to:
1. describe how reinforcement learning problems differ from supervised learning problems such as regression and classification;
2. formulate suitable real-world problems as reinforcement learning problems by defining a state space, an action space, and a reward function appropriate for the context;
3. apply a range of basic solution methods to reinforcement learning problems;
4. appreciate the difficulties encountered in solving large, complex reinforcement learning problems in practice;
5. critically evaluate the relative merits and limitations of various reinforcement learning algorithms. |
| Synopsis: | "This unit introduces thereinforcement learning problem and describes basic solution methods.
" |
| Content: | Topics covered normally include: dynamic programming, Monte Carlo methods, temporal-difference algorithms, integration of planning and learning, value function approximation, and policy gradient methods.
|
| Course availability: |
CM52048 is Optional on the following courses:Department of Computer Science
|
Notes:
|