Matthias Hutsebaut-Buysse
Research Subjects
Matthias Hutsebaut-Buysse has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Kevin Mets
IDLab -Faculty of Applied Engineering University of Antwerp -imec Sint-Pietersvliet 7 2000 Antwerp Antwerp Belgium
3 shared publications - Thomas Avé
IDLab, Department of Computer Science, Sint-Pietersvliet 7, University of Antwerp -imec, Antwerp, Belgium
2 shared publications Kevin Mets
University of Antwerp – imec
1 shared publicationSteven Latré
University of Antwerp – imec
1 shared publication- Steven Latré
Department of Computer Science University of Antwerp imec IDLab Antwerp Belgium
1 shared publication Tom De Schepper
University of Antwerp – imec
1 shared publication
Latest Publications
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (15) , 1
Flexible and Efficient Feature-level Fusion with Wireless Acoustic Sensors using Graph Attention Networks
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (15) , 1
Flexible and Efficient Feature-level Fusion with Wireless Acoustic Sensors using Graph Attention Networks
- Open Access
- 15 October 2025
- Published by Springer Nature in Machine Learning
- Vol. 114 (11) , 1-27
Temporal distillation: compressing a policy in space and time
Deploying deep reinforcement learning on resource-constrained devices remains a significant challenge due to the energy-intensive nature of the sequential decision-making process. Model compression can reduce the spatial (e.g. storage, memory) requirements of a policy network, but this does not always translate to a proportional increase in inference speed and computational efficiency. We introduce a novel temporal compression paradigm that improves the efficiency more directly, by reducing the number of predictions needed to complete a task. This method, based on policy distillation, allows a student model to learn when a change of action will be required by observing sequences of identical actions in the trajectories of an existing teacher model. At each decision, the student can then predict both an action and how many times to perform this action consecutively. This approach allows any existing policy for discrete action spaces to be optimized for energy efficiency through both spatial and temporal compression simultaneously. Experiments on devices ranging from a microcontroller and smartphone processor to a data centre GPU show how this method can decrease the average time it takes to predict an action by up to 13.5 times, compared to 4 times through spatial compression alone, while maintaining a similar average return as the original teacher. In practice, this allows complex models to be deployed on ultra-low-power devices, enabling them to conserve energy by remaining in sleep mode for longer periods, and still achieve high runtime and task performance.
- 15 October 2025
- Published by Springer Nature in Machine Learning
- Vol. 114 (11) , 1-27
Open AccessTemporal distillation: compressing a policy in space and time
Deploying deep reinforcement learning on resource-constrained devices remains a significant challenge due to the energy-intensive nature of the sequential decision-making process. Model compression can reduce the spatial (e.g. storage, memory) requirements of a policy network, but this does not always translate to a proportional increase in inference speed and computational efficiency. We introduce a novel temporal compression paradigm that improves the efficiency more directly, by reducing the number of predictions needed to complete a task. This method, based on policy distillation, allows a student model to learn when a change of action will be required by observing sequences of identical actions in the trajectories of an existing teacher model. At each decision, the student can then predict both an action and how many times to perform this action consecutively. This approach allows any existing policy for discrete action spaces to be optimized for energy efficiency through both spatial and temporal compression simultaneously. Experiments on devices ranging from a microcontroller and smartphone processor to a data centre GPU show how this method can decrease the average time it takes to predict an action by up to 13.5 times, compared to 4 times through spatial compression alone, while maintaining a similar average return as the original teacher. In practice, this allows complex models to be deployed on ultra-low-power devices, enabling them to conserve energy by remaining in sleep mode for longer periods, and still achieve high runtime and task performance.
- Top Cited PapersOpen Access
- 17 February 2022
- Published by MDPI AG in Machine Learning and Knowledge Extraction
- Vol. 4 (1) , 172-221
Hierarchical Reinforcement Learning: A Survey and Open Research Challenges
Reinforcement learning (RL) allows an agent to solve sequential decision-making problems by interacting with an environment in a trial-and-error fashion. When these environments are very complex, pure random exploration of possible solutions often fails, or is very sample inefficient, requiring an unreasonable amount of interaction with the environment. Hierarchical reinforcement learning (HRL) utilizes forms of temporal- and state-abstractions in order to tackle these challenges, while simultaneously paving the road for behavior reuse and increased interpretability of RL systems. In this survey paper we first introduce a selection of problem-specific approaches, which provided insight in how to utilize often handcrafted abstractions in specific task settings. We then introduce the Options framework, which provides a more generic approach, allowing abstractions to be discovered and learned semi-automatically. Afterwards we introduce the goal-conditional approach, which allows sub-behaviors to be embedded in a continuous space. In order to further advance the development of HRL agents, capable of simultaneously learning abstractions and how to use them, solely from interaction with complex high dimensional environments, we also identify a set of promising research directions.
- 17 February 2022
- Published by MDPI AG in Machine Learning and Knowledge Extraction
- Vol. 4 (1) , 172-221
Top Cited PapersOpen AccessHierarchical Reinforcement Learning: A Survey and Open Research Challenges
Reinforcement learning (RL) allows an agent to solve sequential decision-making problems by interacting with an environment in a trial-and-error fashion. When these environments are very complex, pure random exploration of possible solutions often fails, or is very sample inefficient, requiring an unreasonable amount of interaction with the environment. Hierarchical reinforcement learning (HRL) utilizes forms of temporal- and state-abstractions in order to tackle these challenges, while simultaneously paving the road for behavior reuse and increased interpretability of RL systems. In this survey paper we first introduce a selection of problem-specific approaches, which provided insight in how to utilize often handcrafted abstractions in specific task settings. We then introduce the Options framework, which provides a more generic approach, allowing abstractions to be discovered and learned semi-automatically. Afterwards we introduce the goal-conditional approach, which allows sub-behaviors to be embedded in a continuous space. In order to further advance the development of HRL agents, capable of simultaneously learning abstractions and how to use them, solely from interaction with complex high dimensional environments, we also identify a set of promising research directions.
- 10 September 2021
- Published by Springer Nature
- p. 190-205
Disagreement Options: Task Adaptation Through Temporally Extended Actions
- 10 September 2021
- Published by Springer Nature
- p. 190-205
Disagreement Options: Task Adaptation Through Temporally Extended Actions