- Academic Registry
Programme & Unit Catalogues


CM50270: Reinforcement learning

[Page last updated: 27 October 2020]

Follow this link for further information on academic years Academic Year: 2020/1
Further information on owning departmentsOwning Department/School: Department of Computer Science
Further information on credits Credits: 6      [equivalent to 12 CATS credits]
Further information on notional study hours Notional Study Hours: 120
Further information on unit levels Level: Masters UG & PG (FHEQ level 7)
Further information on teaching periods Period:
Semester 2
Further information on unit assessment Assessment Summary: CW 100%
Further information on unit assessment Assessment Detail:
  • Case Study (Written Report and Presentation) (CW 40%)
  • Programming Assignments (CW 60%)
Further information on supplementary assessment Supplementary Assessment:
Like-for-like reassessment (where allowed by programme regulations)
Further information on requisites Requisites:
Description: Aims:
This unit introduces the reinforcement learning problem and describes basic solution methods.

Learning Outcomes:
At the end of this unit, 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. critically evaluate a range of basic solution methods to reinforcement learning problems,
4. analyse the difficulties encountered in solving large, complex reinforcement learning problems in practice.

Skills:
Intellectual skills:
* Develop algorithmic thinking for sequential decision making under uncertainty (T, F, A)
Transferable skills:
* Enhance perspective of decision making (T, F)
* Oral presentation of ones work (F,A)

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.
Further information on programme availabilityProgramme availability:

CM50270 is Optional on the following programmes:

Department of Computer Science Department of Electronic & Electrical Engineering

Notes:

  • This unit catalogue is applicable for the 2020/21 academic year only. Students continuing their studies into 2021/22 and beyond should not assume that this unit will be available in future years in the format displayed here for 2020/21.
  • Programmes 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.