Designing Intelligent Agents
| Code | School | Level | Credits | Semesters |
| COMP4105 | Computer Science | 4 | 20 | Spring UK |
- Code
- COMP4105
- School
- Computer Science
- Level
- 4
- Credits
- 20
- Semesters
- Spring UK
Summary
You'll be given a basic introduction to the analysis and design of intelligent agents, software systems which perceive their environment and act in that environment in pursuit of their goals. Spending around four hours each week in lectures and tutorials, you'll cover topics including task environments, reactive, deliberative and hybrid architectures for individual agents, and architectures and coordination mechanisms for multi-agent systems.
As part of the assessment of this module, you will produce a research paper-style report and deliver a conference-style presentation.
Target Students
Available to Level 4 students in the School of Computer Science. Available for students in MSc Machine Learning in Science. This module is not available to students not listed above without explicit approval from the module convenor(s), and is not available to students taking COMP3004. This module is part of the Artificial Intelligence, Modelling and Optimisation theme in the School of Computer Science.
Assessment
- 90% Coursework 1: Portfolio of practical work. Report (4000 words in the style of a scientific paper), or 20-minute video, or 20-minute podcast summarising the work.
- 10% Coursework 2: 15-minute research-style presentation, explaining the practical work and its connections to research in the discipline.
Assessed by end of spring semester
Educational Aims
To develop a basic understanding of the problems and techniques of building intelligent agents.To give an appreciation of the trade-offs inherent in the design of agent-based systems.To illustrate these through a project involving the construction of simple (multi-)agent-based systems.To develop new analysis and design skills appropriate to more complex Al problems.Learning Outcomes
Knowledge and Understanding
- Understanding of the problems and techniques in the design of intelligent agents, knowledge of common agent architectures.
Intellectual Skills
- The ability to understand and logically evaluate agents' requirements and specifications.
- The ability to analyse agent behaviour in a variety of environments.
- An appreciation of the use of Machine learning methods to the design of intelligent agents.
Professional Skills
- Enhanced Al programming skills.
Transferable Skills
- Enhanced systems analysis and design skills.
- Delivery of a conference-style research presentation.
- Presenting work in a professional manner.