Improving DreamerV2 by Identifying Irrelevant Environmental Features

Simple item page
dc.contributor.advisorAmbrogioni, L.
dc.contributor.advisorGerven, van, M.A.J.
dc.contributor.authorVoort, van der , Noah
dc.date.issued2022-06-20
dc.description.abstractThis thesis introduces DreamerV3. A modified version of the model-based reinforcement learning algorithm DreamerV2. The thesis outlines the shortcomings of DreamerV2 and motivates the proposed solution. The performance of DreamerV3 is tested on the Atari Video Pinball environment and a modified Atari Pong environment. A significant performance increase over DreamerV2 is demonstrated in the modified Pong environment, but no performance increase is attained for the Video Pinball environment.
dc.identifier.urihttps://theses.ubn.ru.nl/handle/123456789/16005
dc.language.isoen
dc.thesis.facultyFaculteit der Sociale Wetenschappen
dc.thesis.specialisationspecialisations::Faculteit der Sociale Wetenschappen::Artificial Intelligence::Bachelor Artificial Intelligence
dc.thesis.studyprogrammestudyprogrammes::Faculteit der Sociale Wetenschappen::Artificial Intelligence
dc.thesis.typeBachelor
dc.titleImproving DreamerV2 by Identifying Irrelevant Environmental Features
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
Voort, van der, N. s-1001198-Thesis-2022.pdf
Size:
1.1 MB
Format:
Adobe Portable Document Format
Download
Collections
Faculteit der Sociale Wetenschappen