Regular Decision Processes for Grid Worlds

Autor: Lenaers, Nicky, van Otterlo, Martijn

Markov decision processes are typically used for sequential decision making under uncertainty. For many aspects however, ranging from constrained or safe specifications to various kinds of temporal (non-Markovian) dependencies in task and reward stru

Externí odkaz: http://arxiv.org/abs/2111.03647

Gatekeeping Algorithms with Human Ethical Bias: The ethics of algorithms in archives, libraries and society

Autor: van Otterlo, Martijn

In the age of algorithms, I focus on the question of how to ensure algorithms that will take over many of our familiar archival and library tasks, will behave according to human ethical norms that have evolved over many years. I start by characterizi

Externí odkaz: http://arxiv.org/abs/1801.01705

There are plenty of places like home: Using relational representations in hierarchies for distance-based image understanding

Autor: Antanas, Laura, van Otterlo, Martijn, Oramas Mogrovejo, José, Tuytelaars, Tinne, De Raedt, Luc

Publikováno v: In Neurocomputing 10 January 2014 123:75-85

End-to-End Personalization of Digital Health Interventions using Raw Sensor Data with Deep Reinforcement Learning

Autor: El Hassouni, Ali, Hoogendoorn, Mark, Eiben, A. E., Van Otterlo, Martijn, Muhonen, Vesa

Publikováno v: El Hassouni, A, Hoogendoorn, M, Eiben, A E, Van Otterlo, M & Muhonen, V 2019, End-to-End Personalization of Digital Health Interventions using Raw Sensor Data with Deep Reinforcement Learning : A comparative study in digital health interventions for behavior change . in P Barnaghi, G Gottlob, Y Manolopoulos, T Tzouramanis & A Vakali (eds), Proceedings-WI '19 : IEEE/WIC/ACM International Conference on Web Intelligence q . Proceedings-2019 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2019, Association for Computing Machinery, Inc, New York, NY, pp. 258-264, 19th IEEE/WIC/ACM International Conference on Web Intelligence, WI 2019, Thessaloniki, Greece, 13/10/19 . https://doi.org/10.1145/3350546.3352527

We introduce an end-to-end reinforcement learning (RL) solution for the problem of sending personalized digital health interventions. Previous work has shown that personalized interventions can be obtained through RL using simple, discrete state info

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::c1e0ad5428d15e880c4d285ba4b360e8
http://www.scopus.com/inward/record.url?scp=85074749219&partnerID=8YFLogxK

Project BLIIPS: Making the Physical Public Library more Intelligent through Artificial Intelligence.

Autor: van Otterlo, Martijn¹

Publikováno v: Qualitative & Quantitative Methods in Libraries. Jun2016, Vol. 5 Issue 2, p287-300. 14p.