Official course description:
Full info last published 15/05-22

Deep Learning for Games and Simulations

Course info
Language:
English
ECTS points:
15
Course code:
KGDELGS1KU
Participants max:
40
Offered to guest students:
yes
Offered to exchange students:
yes
Offered as a single subject:
yes
Price for EU/EEA citizens (Single Subject):
21250 DKK
Programme
Level:
MSc. Master
Programme:
MSc in Games
Staff
Course manager
Assistant Professor
Teacher
Postdoc
Teacher
Postdoc
Teacher
Full Professor
Teaching Assistant
Teaching Assistant (TA)
Course semester
Semester
Efterår 2022
Start
29 August 2022
End
31 January 2023
Exam
Exam type
ordinær
Internal/External
ekstern censur
Grade Scale
7-trinsskala
Exam Language
GB
Abstract

The goal of the course is to teach the understanding, design, implementation, and use of modern artificial intelligence (AI) techniques for generating efficient, intelligent behaviors in games and other simulation environments. A particular focus is given to techniques applied to agent-based simulations.


Description

Artificial intelligence has many applications, and many techniques need to be applied in simulated environments, whether during the training (as in robotics or systems simulations) or deployment (such as in computer games). The topics covered in this course apply to games, simulation environments, robotics, and many other areas.

Students will learn a broad understanding of AI algorithms' theoretical, practical, and implementation sides.

The course will partly cover the following topics (AI techniques and problems): 

  • neural networks,
  • deep reinforcement learning, 
  • evolutionary algorithms, 
  • neuroevolution,
  • Monte Carlo Tree Search (MCTS), 
  • hybrid approaches (MCTS+Neural networks), 
  • adversarial search,
  • multi-agent learning,
  • as well as the overview of the latest applications of these techniques in the industry.

Formal prerequisites

Students must have completed a course on programming such as "Introductory Programming" or "Object-Oriented Programming." Furthermore, the student should have familiarity with basic reinforcement learning and graph search algorithms. We will mainly use the Python programming language during the course, so familiarity with the language is an advantage.


Intended learning outcomes

After the course, the student should be able to:

  • Theorize about and describe the AI algorithms covered in the class
  • Identify tasks that can be tackled through advanced AI techniques and select the appropriate technique for the problem under investigation
  • Compare the performance of different AI techniques and reflect on their suitability for different domains
  • Design and implement efficient and robust advanced AI algorithms
  • Work efficiently in groups
Learning activities

6 weeks of intensive lectures + mandatory individual assignment (see below). 

8 weeks of group project work with supervision (There are some lectures during this period).

Students are responsible for attending lectures (some of which will likely be by outside guest speakers) and working on their projects independently (individual mandatory assignment) or in groups.

Besides the hours planned for lectures, there are tutorials, exercises, and supervision sessions that complement the theory covered during the lectures and are necessary for meeting the course's learning objectives. Students will practice presenting their work during the course to prepare for the oral exam. Lectures provide theoretical foundations and walk-through examples of relevant AI algorithms, while exercises focus on students discussing and implementing the central algorithms themselves.


Mandatory activities

During this course, students will have to hand in an individual mandatory assignment (6 pages written report + source code) that needs to be completed/approved before being eligible for the examination.

The mandatory assignment deadline will be on learnIT. 

The student will receive the grade NA (not approved) at the ordinary exam; if the mandatory activities are not approved, the student will use an exam attempt.


The student will receive the grade NA (not approved) at the ordinary exam, if the mandatory activities are not approved and the student will use an exam attempt.

Course literature

We will publish the course literature on the course page in LearnIT.


Student Activity Budget
Estimated distribution of learning activities for the typical student
  • Preparation for lectures and exercises: 20%
  • Lectures: 20%
  • Exercises: 10%
  • Assignments: 20%
  • Project work, supervision included: 20%
  • Exam with preparation: 10%
Ordinary exam
Exam type:
D: Submission of written work with following oral, External (7-point scale)
Exam variation:
D2G: Submission for groups with following oral exam supplemented by the submission. Shared responsibility for the report.
Exam submisson description:
The written work is a group project report (written work + source code + video production).
Group submission:
Group
  • Group size is 2-3 people
Exam duration per student for the oral exam:
30 minutes
Group exam form:
Mixed exam 2 : Joint student presentation followed by an individual dialogue. The group makes their presentations together and afterwards the students participate in the dialogue individually while the rest of the group is outside the room.


reexam
Exam type:
D: Submission of written work with following oral, External (7-point scale)
Exam variation:
D2G: Submission for groups with following oral exam supplemented by the submission. Shared responsibility for the report.

Time and date
Ordinary Exam - submission Fri, 16 Dec 2022, 08:00 - 14:00
Ordinary Exam Mon, 16 Jan 2023, 09:00 - 21:00
Ordinary Exam Tue, 17 Jan 2023, 09:00 - 21:00