Browsing AURA by Author "Andersen, Per-Arne"
Now showing items 21-28 of 28
-
The Dreaming Variational Autoencoder for Reinforcement Learning Environments
Andersen, Per-Arne; Goodwin, Morten; Granmo, Ole-Christoffer (Journal article; Peer reviewed, 2018)Reinforcement learning has shown great potential in generalizing over raw sensory data using only a single neural network for value optimization. There are several challenges in the current state-of-the-art reinforcement ... -
The Potential and Limitations of the Tsetlin Machine in Model-Free Reinforcement Learning
Grimsmo, Andreas; Drøsdal, Didrik Kallhovd (Master thesis, 2023)This paper aims to investigate the potential of model-free reinforcement learning using the Tsetlin Machine by evaluating its performance in widely recognized benchmark environments for reinforcement learning: Cartpole and ... -
The Potential and Limitations of the Tsetlin Machine in Model-Free Reinforcement Learning
Drøsdal, Didrik Kallhovd; Grimsmo, Andreas (Master thesis, 2023)This paper aims to investigate the potential of model-free reinforcement learning using the Tsetlin Machine by evaluating its performance in widely recognized benchmark environments for reinforcement learning: Cartpole and ... -
Towards a deep reinforcement learning approach for Tower Line Wars
Andersen, Per-Arne; Goodwin, Morten; Granmo, Ole-Christoffer (Lecture Notes in Artificial Intelligence (LNAI), Journal article; Peer reviewed, 2017)There have been numerous breakthroughs with reinforcement learning in the recent years, perhaps most notably on Deep Reinforcement Learning successfully playing and winning relatively advanced computer games. There is ... -
Towards safe reinforcement-learning in industrial grid-warehousing
Andersen, Per-Arne; Goodwin, Morten; Granmo, Ole-Christoffer (Peer reviewed; Journal article, 2020) -
Transformer Reinforcement Learning for Procedural Level Generation
Mrozik, Lukasz Filip; Aas, Sebastian Bekkvik (Master thesis, 2023)This paper examines how recent advances in sequence modeling translate for machine learning assisted procedural level generation. We explore the use of Transformer based models like DistilGPT-2 to generate platformer levels, ... -
Transformer Reinforcement Learning for Procedural Level Generation
Mrozik, Lukasz Filip; Aas, Sebastian Bekkvik (Master thesis, 2023)This paper examines how recent advances in sequence modeling translate for machine learning assisted procedural level generation. We explore the use of Transformer based models like DistilGPT-2 to generate platformer levels, ... -
Utilizing Reinforcement Learning and Computer Vision in a Pick-And-Place Operation for Sorting Objects in Motion
Solberg, Trygve Andre Olsøy; Sand, Kristoffer (Master thesis, 2023)This master's thesis studies the implementation of advanced machine learning (ML) techniques in industrial automation systems, focusing on applying machine learning to enable and evolve autonomous sorting capabilities in ...