Reinforcement Learning
Course, Master's level, 1RT747
Spring 2024 Spring 2024, Uppsala, 50%, On-campus, English
- Location
- Uppsala
- Pace of study
- 50%
- Teaching form
- On-campus
- Instructional time
- Daytime
- Study period
- 18 March 2024–2 June 2024
- Language of instruction
- English
- Entry requirements
-
120 credits including Probability and Statistics, Linear Algebra II, Single Variable Calculus and 10 credits of programming. Proficiency in English equivalent to the Swedish upper secondary course English 6.
- Selection
-
Higher education credits in science and engineering (maximum 240 credits)
- Fees
-
If you are not a citizen of a European Union (EU) or European Economic Area (EEA) country, or Switzerland, you are required to pay application and tuition fees.
- Application fee: SEK 900
- First tuition fee instalment: SEK 18,125
- Total tuition fee: SEK 18,125
- Application deadline
- 16 October 2023
- Application code
- UU-61800
Admitted or on the waiting list?
- Registration period
- 4 March 2024–25 March 2024
- Information on registration.
Spring 2024 Spring 2024, Uppsala, 50%, On-campus, English For exchange students
- Location
- Uppsala
- Pace of study
- 50%
- Teaching form
- On-campus
- Instructional time
- Daytime
- Study period
- 18 March 2024–2 June 2024
- Language of instruction
- English
- Entry requirements
-
120 credits including Probability and Statistics, Linear Algebra II, Single Variable Calculus and 10 credits of programming. Proficiency in English equivalent to the Swedish upper secondary course English 6.
Admitted or on the waiting list?
- Registration period
- 4 March 2024–25 March 2024
- Information on registration.
About the course
This course gives a solid introduction to the modern tools used to devise, implement and analyse reinforcement learning algorithms, and also introduces some key concepts from feedback control. The course covers feedback control systems, Markov decision processes, planning by dynamic programming, model-free prediction and control, learning with function approximations and deep Q-learning. Possible applications discussed during the course include classical control problems like the inverted pendulum, as well as robotics and video games.