Skip to main content

Reinforcement Learning E-MDS130

This course introduces AI and optimization in a fun, easy, interesting, immersive, and hands-on way. Optimization problems are becoming essential across multiple disciplines. Through this course you learn how to use efficient optimization strategies in work processes.

Publisert: Endret:


Next course

Spring 2022



Application deadline


Teaching method


Course fee

Free of charge, except for course material.

Course content

This digital course gives you an introduction to efficient optimazation strategies, for instance: optimization of complex machine learning models to make them more efficient, creating exploratory models that without training can evaluate a situation and gradually make positive decisions, explore financial data to discover patterns that lead to beneficial outcomes, create agents to play video games and more.

Reinforcement learning

Concepts covered in this course provides relevant theoretical and hands-on programming knowledge. Every topic is demonstrated using easy-to-understand real-world examples.

The following topics will be covered during the course duration:

  • Topic 1: Reinforcement Learning - an introduction
  • Topic 2: Course Materials, Supplementary Resources, and Development Environment
  • Topic 3: Tabular Methods
  • Topic 4: Dynamic Programming
  • Topic 5: Monte-Carlo & Temporal Difference and Q-Learning
  • Topic 6: Policy Gradients
  • Topic 7: The Actor-Critic Method
  • Topic 8: Deep Q-Network - an Overview
  • Topic 9: Further Exploration

Target group

The target group for this course is professionals and students working or interested in areas of artificial intelligence, machine learning, game theory, control theory, operations research, information theory, simulation-based optimization, multi-agent systems, swarm intelligence, and statistics.

Form of Work

  • Teaching language: English
  • A total of 10 - 12 lectures covers the course syllabus
  • Every lecture is covered through bite-size recorded videos
  • Three hands-on use-case based assignments will be presented to the students
  • Four live sessions is conducted to discuss the solutions for each assignment


  • Good programming knowledge
  • Knowledge of basic algebra, probability, and statistics
  • Python Programming Knowledge
  • Understanding of Numpy, Matplotlib

Mandatory requriements

  • Bachelor Degree 180 ECTS
  • Foreign applicants must also document education and English skills in accordance with NOKUT's regulations.


  • Individual home exam - all aids available
  • 75 multiple choice questions
  • Exam date: 20 May 2022
  • Grading: A- F

Conditions for taking the exam/assessment

  • The three assignments are mandatory - approved / not approved
  • Submissions should provide coding solutions to the respective problems with proper documentation

Please note that changes may occur.


Faculty of Science and Technology

Department of Electrical Engineering and Computer Science

Administrational contact persons

Senior rådgiver
Division of Education

UiS Lifelong Learning
Division of Education

UiS Lifelong Learning