Improving DreamerV2 by Identifying Irrelevant Environmental Features

Keywords
Loading...
Thumbnail Image
Issue Date
2022-06-20
Language
en
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
This 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.
Description
Citation
Faculty
Faculteit der Sociale Wetenschappen