Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Denis Steckelmacher

Synthesising Reinforcement Learning Policies through Set-Valued Inductive Rule Learning


Jun 10, 2021
Youri Coppens, Denis Steckelmacher, Catholijn M. Jonker, Ann Nowé

* Trustworthy AI - Integrating Learning, Optimization and Reasoning (2021), Lecture Notes in Computer Science, vol. 12641, pp. 163-179 
* 17 pages, 4 figures. The final authenticated publication is available online at https://doi.org/10.1007/978-3-030-73959-1_15 

  Access Paper or Ask Questions

Transfer Learning Across Simulated Robots With Different Sensors


Jul 18, 2019
Hélène Plisnier, Denis Steckelmacher, Diederik Roijers, Ann Nowé


  Access Paper or Ask Questions

Sample-Efficient Model-Free Reinforcement Learning with Off-Policy Critics


Mar 11, 2019
Denis Steckelmacher, Hélène Plisnier, Diederik M. Roijers, Ann Nowé


  Access Paper or Ask Questions

The Actor-Advisor: Policy Gradient With Off-Policy Advice


Feb 07, 2019
Hélène Plisnier, Denis Steckelmacher, Diederik M. Roijers, Ann Nowé


  Access Paper or Ask Questions

Dynamic Weights in Multi-Objective Deep Reinforcement Learning


Sep 20, 2018
Axel Abels, Diederik M. Roijers, Tom Lenaerts, Ann Nowé, Denis Steckelmacher


  Access Paper or Ask Questions

Directed Policy Gradient for Safe Reinforcement Learning with Human Advice


Aug 13, 2018
Hélène Plisnier, Denis Steckelmacher, Tim Brys, Diederik M. Roijers, Ann Nowé

* Accepted at the European Workshop on Reinforcement Learning 2018 (EWRL14) 

  Access Paper or Ask Questions

Reinforcement Learning in POMDPs with Memoryless Options and Option-Observation Initiation Sets


Sep 12, 2017
Denis Steckelmacher, Diederik M. Roijers, Anna Harutyunyan, Peter Vrancx, Hélène Plisnier, Ann Nowé


  Access Paper or Ask Questions

An Empirical Comparison of Neural Architectures for Reinforcement Learning in Partially Observable Environments


Dec 17, 2015
Denis Steckelmacher, Peter Vrancx

* Presented at the 27th Benelux Conference on Artificial Intelligence 

  Access Paper or Ask Questions