Denis Steckelmacher

Postdoc, Vrije Universiteit Brussel

Joined

April 2019

Names

Denis Steckelmacher (Preferred)

Emails

****@ai.vub.ac.be (Confirmed)

****@vub.be (Confirmed)

Personal Links

Homepage

DBLP

ORCID

Career & Education History

Postdoc

Vrije Universiteit Brussel (vub.be)

2020 – Present

PhD student

Vrije Universiteit Brussel (vub.ac.be)

2016 – 2020

Advisors, Relations & Conflicts

PhD Advisor

Ann Nowé

2016 – 2020

Expertise

reinforcement learning

sample-efficiency

actor-critic

policy gradient

Present

Publications

Explainable RL Policies by Distilling to Locally-Specialized Linear Policies with Voronoi State Partitioning
Senne Deproost, Denis Steckelmacher, Ann Nowe
- BNAIC/BeNeLearn 2025 Poster
- Readers: Everyone
Synergistic Task and Motion Planning With Reinforcement Learning-Based Non-Prehensile Actions
Gaoyuan Liu, Joris De Winter, Denis Steckelmacher, Roshan Kumar Hota, Ann Nowé, Bram Vanderborght
- May 2023 (modified: 24 Apr 2023)
- IEEE Robotics Autom. Lett. 2023
- Readers: Everyone
Synergistic Task and Motion Planning with Reinforcement Learning Non-Prehensile Actions
Gaoyuan Liu, Joris De Winter, Denis Steckelmacher, Roshan Kumar Hota, Ann Nowe, Bram Vanderborght
- 30 Mar 2023
- OpenReview Archive Direct Upload
- Readers: Everyone
Transferring Multiple Policies to Hotstart Reinforcement Learning in an Air Compressor Management Problem
Hélène Plisnier, Denis Steckelmacher, Jeroen Willems, Bruno Depraetere, Ann Nowe
- 30 Mar 2023
- OpenReview Archive Direct Upload
- Readers: Everyone
Model-free control of compressors in an air network with unknown future air demand
Jeroen Willems, Denis Steckelmacher, Bruno Depraetere, Ann Nowe
- 30 Mar 2023
- OpenReview Archive Direct Upload
- Readers: Everyone
Transferring Multiple Policies to Hotstart Reinforcement Learning in an Air Compressor Management Problem
Hélène Plisnier, Denis Steckelmacher, Jeroen Willems, Bruno Depraetere, Ann Nowé
- 2023 (modified: 24 Apr 2023)
- CoRR 2023
- Readers: Everyone
Fast Initialization of Control Parameters using Supervised Learning on Data from Similar Assets
Jeroen Willems, Kerem Eryilmaz, Denis Steckelmacher, Bruno Depraetere, Rian Beck, Abdellatif Bey-Temsamani, Jan Helsen, Ann Nowé
- 2022 (modified: 24 Apr 2023)
- CCTA 2022
- Readers: Everyone
MoveRL: To a Safer Robotic Reinforcement Learning Environment
Gaoyuan Liu, Joris De Winter, Bram Vanderborght, Ann Nowé, Denis Steckelmacher
- 2021 (modified: 24 Apr 2023)
- BNAIC/BENELEARN 2021
- Readers: Everyone
Explainable Reinforcement Learning Through Goal-Based Interpretability
Gregory Bonaert, Youri Coppens, Denis Steckelmacher, Ann Nowe
- 28 Sept 2020 (modified: 05 May 2023)
- ICLR 2021 Conference Blind Submission
- Readers: Everyone
Dynamic Weights in Multi-Objective Deep Reinforcement Learning
Axel Abels, Diederik M. Roijers, Tom Lenaerts, Ann Nowé, Denis Steckelmacher
- 2019 (modified: 11 Nov 2022)
- ICML 2019
- Readers: Everyone

View all 21 publications