CM32032: 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: | Honours (FHEQ level 6) |
| Period: |
- Academic Year
|
| Assessment Summary: | CWPG 100% |
| Assessment Detail: |
- Project output Group (CWPG 100%)
|
| Supplementary Assessment: |
- CM32032 Reassessment Project output Individual (where allowed by programme regulations)
|
| Requisites: |
In taking this module you cannot take CM52048
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.
|
| Synopsis: | You will explore reinforcement learning as a problem-solving method, and how it differs from other fundamental techniques such as supervised and unsupervised learning. You will learn to formulate real-world problems as reinforcement learning problems, to apply basic solution methods, and to appreciate the difficulties involved in large, complex reinforcement learning problems in practice.
|
| 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: |
CM32032 is Optional on the following courses:
Department of Computer Science
- USCM-AFB30 : BSc(Hons) Computer Science (Year 3)
- USCM-AAB07 : BSc(Hons) Computer Science with Study year abroad (Year 4)
- USCM-AKB07 : BSc(Hons) Computer Science with Year long work placement (Year 4)
- USCM-AFB31 : BSc(Hons) Computer Science and Artificial Intelligence (Year 3)
- USCM-AAB27 : BSc(Hons) Computer Science and Artificial Intelligence with Study year abroad (Year 4)
- USCM-AKB27 : BSc(Hons) Computer Science and Artificial Intelligence with Year long work placement (Year 4)
- USCM-AFB32 : BSc(Hons) Computer Science and Mathematics (Year 3)
- USCM-AAB20 : BSc(Hons) Computer Science and Mathematics with Study year abroad (Year 4)
- USCM-AKB20 : BSc(Hons) Computer Science and Mathematics with Year long work placement (Year 4)
- USCM-AFM30 : MComp(Hons) Computer Science (Year 3)
- USCM-AFM31 : MComp(Hons) Computer Science and Artificial Intelligence (Year 3)
- USCM-AKM31 : MComp(Hons) Computer Science and Artificial Intelligence with professional placement (Year 3)
- USCM-AKM31 : MComp(Hons) Computer Science and Artificial Intelligence with study abroad (Year 3)
- USCM-AFM32 : MComp(Hons) Computer Science and Mathematics (Year 3)
- USCM-AKM32 : MComp(Hons) Computer Science and Mathematics with professional placement (Year 3)
- USCM-AKM32 : MComp(Hons) Computer Science and Mathematics with study abroad (Year 3)
- USCM-AKM30 : MComp(Hons) Computer Science with professional placement (Year 3)
- USCM-AKM30 : MComp(Hons) Computer Science with study abroad (Year 3)
|
Notes: - This unit catalogue is applicable for the 2025/26 academic year only. Students continuing their studies into 2026/27 and beyond should not assume that this unit will be available in future years in the format displayed here for 2025/26.
- 好色tv and units are subject to change in accordance with normal University procedures.
- Availability of units will be subject to constraints such as staff availability, minimum and maximum group sizes, and timetabling factors as well as a student's ability to meet any pre-requisite rules.
- Find out more about these and other important University terms and conditions here.
|
