Valid from: Spring 2019
Decided by: Professor Thomas Johansson
Date of establishment: 2019-09-12
Division: Automatic Control
Course type: Third-cycle course
Teaching language: English
To become familiar with reinforcement learning.
Knowledge and Understanding
For a passing grade the doctoral student must - understand the basic concepts and methods of reinforcement learning
Competences and Skills
For a passing grade the doctoral student must - be able to understand the implementation of reinforcement learning using Python and Tensorflow
Judgement and Approach
For a passing grade the doctoral student must - understand for which problems reinforcement learning is suitable
- Markov Decision Processes - Dynamic programming - Iterative policy evaluation - Iterative policy iteration - Value iteration - Model-free planning - Monte-Carlo methods - Model-free control - Value Function Approximation - Policy Gradient Methods - Exploration and Exploitation
The course is based on video lectures by David Silver.
Types of instruction: Seminars, exercises, self-study literature review, miscellaneous. Based on the Reinforcement Learning Course given by David Silver at UCL and the associated video presentations.
Examination format: Miscellaneous.
Sufficient active participation in the course meetings
Grading scale: Failed, pass
Admission requirements: Admitted to PhD program at an engineering faculty
Assumed prior knowledge: None
Selection criteria: None
Web page: http://www.control.lth.se/education/doctorate-program/study-circle-in-reinforcement-learning/