| CODE | ARI2204 | ||||||||||||
| TITLE | Reinforcement Learning | ||||||||||||
| UM LEVEL | 02 - Years 2, 3 in Modular Undergraduate Course | ||||||||||||
| MQF LEVEL | 5 | ||||||||||||
| ECTS CREDITS | 5 | ||||||||||||
| DEPARTMENT | Artificial Intelligence | ||||||||||||
| DESCRIPTION | Reinforcement Learning is a family of techniques where an intelligent agent learns how to act by analysing the results of performing actions. It has numerous applications, including robotics, algorithmic trading, autonomous driving and game playing. Success stories include Google DeepMind's AlphaGo, which defeated the highest ranking human Go champion. This study-unit will cover the fundamental techniques, together with example applications of how Reinforcement Learning can be used. The student will be introduced to a number of topics such as: - Modelling Reinforcement Learning tasks - Markov Decision Processes - Armed Bandit Methods - Dynamic Programming - Monte-Carlo Methods - Temporal Difference Learning - Integrating Reinforcement Learning with Planning for Model-Based problems. Study-unit Aims: - Introduce students to the field of Reinforcement Learning; - Provide students with enough knowledge to be able to recognize the characteristics of a task that might be a good candidate for Reinforcement Learning techniques; - Demonstrate how a task can be formulated as a Reinforcement Learning task; - Teach students the various techniques of Reinforcement Learning, together with their strenghts and weaknesses and where they can be used effectively. Learning Outcomes: 1. Knowledge & Understanding By the end of the study-unit the student will be able to: - Formulate a task as a Reinforcement Learning task; - Explain the difference between the various Reinforcement Learning techniques; - Determine which technique works best for a given task. 2. Skills By the end of the study-unit the student will be able to: - Determine whether a task can be solved with one of the Reinformcent Learning techniques available; - Apply Reinforcement Learning to a specific task; - Build a system that makes use of one or more Reinforcement Learning algorithms. Main Text/s and any supplementary readings: Main Text: - Sutton, Richard S., and Barto, Andrew G., "Reinforcement Learning: An Introduction", MIT Press, 2nd Edition, 2018, ISBN13: 978-0262039246, online: http://incompleteideas.net/book/the-book.html Supplementary Reading: - Russell, Stuart and Norvig, Peter, "Chapter 21 - Reinforcement Learning" in "Artifical Intelligence: A Modern Approach", Pearson, 3rd Edition, 2016. ISBN-13: 978-1292153964. - Poole D.L., and Mackworth A. K. "Chapter 10 - Planning with Uncertainty" in "Artificial Intelligence: Foundations of Computational Agents", Cambridge University Press, 2nd Edition, 2017, ISBN: 9781107195394, online: https://artint.info/ |
||||||||||||
| ADDITIONAL NOTES | Pre-Requisite Study-unit: ICS1020 | ||||||||||||
| STUDY-UNIT TYPE | Lecture, Independent Study and Project | ||||||||||||
| METHOD OF ASSESSMENT |
|
||||||||||||
| LECTURER/S | Josef Bajada |
||||||||||||
|
The University makes every effort to ensure that the published Courses Plans, Programmes of Study and Study-Unit information are complete and up-to-date at the time of publication. The University reserves the right to make changes in case errors are detected after publication.
The availability of optional units may be subject to timetabling constraints. Units not attracting a sufficient number of registrations may be withdrawn without notice. It should be noted that all the information in the description above applies to study-units available during the academic year 2024/5. It may be subject to change in subsequent years. |
|||||||||||||