Reviewing machine learning of corrosion prediction in a data-oriented perspective

Autor: Leonardo Bertolucci Coelho, Dawei Zhang, Yves Van Ingelgem, Denis Steckelmacher, Ann Nowé, Herman Terryn

Publikováno v: npj Materials Degradation, Vol 6, Iss 1, Pp 1-16 (2022)

Abstract This work provides a data-oriented overview of the rapidly growing research field covering machine learning (ML) applied to predicting electrochemical corrosion. Our main aim was to determine which ML models have been applied and how well th

Externí odkaz: https://doaj.org/article/ca7eae315269463ab1263934edbe3b57

Synergistic Task and Motion Planning With Reinforcement Learning-Based Non-Prehensile Actions

Autor: Gaoyuan Liu, Joris de Winter, Denis Steckelmacher, Roshan Kumar Hota, Ann Nowe, Bram Vanderborght

obotic manipulation in cluttered environments requires synergistic planning among prehensile and non-prehensile actions. Previous works on sampling-based Task and Motion Planning (TAMP) algorithms, e.g. PDDLStream, provide a fast and generalizable so

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1915e021511d180e35a31f741b650696
https://doi.org/10.1109/lra.2023.3261708

Fast initialization of control parameters using supervised learning on data from similar assets

Autor: Jeroen Willems, Kerem Eryilmaz, Denis Steckelmacher, Bruno Depraetere, Rian Beck, Abdellatif Bey-Temsamani, Jan Helsen, Ann Nowe

This paper proposes a method to provide a good initialization of control parameters to be found when performing manual or automated control tuning during development, commissioning or periodic retuning. The method is based on treating the initializat

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f7ec7315fad0570b40c93e9db6e75b67
https://hdl.handle.net/20.500.14017/8be5451e-e72a-47a4-80ff-1f75f6f714f9

Multi-objective reinforcement learning for the expected utility of the return

Autor: Diederik Roijers, Denis Steckelmacher, Ann Nowé

Publikováno v: Vrije Universiteit Brussel
Roijers, D M, Steckelmacher, D & Nowé, A 2020, ' Multi-objective reinforcement learning for the expected utility of the return ', Paper presented at 2018 Adaptive Learning Agents, ALA 2018-Co-located Workshop at the Federated AI Meeting, FAIM 2018, Stockholm, Sweden, 14/07/18-15/07/18 .
Vrije Universiteit Amsterdam
2018 Adaptive Learning Agents, ALA 2018-Co-located Workshop at the Federated AI Meeting, FAIM 2018

Real-world decision problems often have multiple, possibly conflicting, objectives. In multi-objective reinforcement learning, the effects of actions in terms of these objectives must be learned by interacting with an environment. Typically, multi-ob

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::19d2151881af9b1c14b4fb63d8826404
http://www.scopus.com/inward/record.url?scp=85086287094&partnerID=8YFLogxK

Transfer Reinforcement Learning across Environment Dynamics with Multiple Advisors

Autor: Helene Plisnier, Denis Steckelmacher, Roijers, Diederik M., Ann Nowe

Publikováno v: Scopus-Elsevier
Vrije Universiteit Brussel

Sample-efficiency is crucial in reinforcement learning tasks, especially when a large number of similar yet distinct tasks have to be learned. For example, consider a smart wheelchair learning to exit many differently-furnished offices on a building

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::0cf0fecb5c66e6c47b750e617f2c33b6
https://biblio.vub.ac.be/vubir/transfer-reinforcement-learning-across-environment-dynamics-with-multiple-advisors(49b4f0e2-4ff6-401a-8cf3-9a6504f822e5).html