15 December 2023

On the 8th of December, Johan Källström at the Department of Computer and Information Science defended his thesis about reinforcement learning, a machine learning method, and its utility for simulation-based pilot training. Here is a brief summary of the thesis.

The cockpit of a Gripen E flight simulator
The cockpit of a Gripen E flight simulator Photographer: Per Kustvik, Saab AB

Team training in complex domains often requires a substantial number of resources, e.g. vehicles, machines, and role-players. For this reason, it may be difficult to realise efficient and effective training scenarios in a real-world setting. Instead, part of the training can be conducted in synthetic, computer-generated environments.

Reinforcement learning for improved utility of simulation-based training

In his doctoral thesis, Johan Källström has studied how the machine learning method reinforcement learning can be used to construct synthetic agents in support of simulation-based pilot training. The focus has been on methods that can find a balance between multiple objectives, for instance different training objectives, to optimise the utility of the user. The thesis presents agents that can provide support to instructors by efficient learning of a set of Pareto optimal policies, and by efficient adaptation to user needs in operational training systems.

To the thesis: Reinforcement learning for improved utility of simulation-based training

Frans Oliehoek hands over a document to Johan KällströmJohan Källström, to the left, and Frans Oliehoek, University of Technology, The Netherlands, Chair of examining committee. Photo credit David Bergström

Doctoral studies in computer and information science

Organisation

Latest news from LiU

Close-up of a hand putting a ballot into a box

How local democracy can be strengthened

At a time when the values of democracy are under threat, municipalities need to resist authoritarian tendencies. Certain reforms can contribute to a more resilient local democracy. The introduction of municipal parliamentarism is an example.

Six people looking at a laptopscreen.

LiU in collaboration with NASA

A collaboration between Linköping University and NASA has led to a new three-day workshop about managing the unexpected. The aim is to provide knowledge, and some experience, of decision-making in tough situations.

Red blood cell.

AI method for determining time of death is awarded prize

Jenny Arpe’s master’s thesis at LiU presents a new method for determining the time of death using AI. For this she has now been awarded a master of science in engineering thesis prize awarded in memory of Christopher Polhem.