Denis Steckelmacher

发表

Directed Policy Gradient for Safe Reinforcement Learning with Human Advice pdf

Tim Brys, Ann Nowé, Diederik M. Roijers, 2018, ArXiv.

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

Peter Vrancx, Ann Nowé, Diederik M. Roijers, 2017, AAAI.

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

Ann Nowé, Diederik M. Roijers, Hélène Plisnier, 2019, ArXiv.

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

Ann Nowé, Diederik M. Roijers, Hélène Plisnier, 2019, BNAIC/BENELEARN.

Transfer Reinforcement Learning across Environment Dynamics with Multiple Advisors

Ann Nowé, Diederik M. Roijers, Hélène Plisnier, 2019, BNAIC/BENELEARN.

Multi-objective Reinforcement Learning for the Expected Utility of the Return

Ann Nowé, Diederik M. Roijers, Denis Steckelmacher, 2020 .

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

Peter Vrancx, Denis Steckelmacher, 2015, ArXiv.

Reinforcement learning in complex environments: Evaluating algorithms on image classification, Informatique

Tom Lenaerts, Denis Steckelmacher, T. Lenaerts, 2016 .

A Motorized Wheelchair that Learns to Make its Way through a Crowd

Ann Nowé, Hélène Plisnier, Denis Steckelmacher, 2019, BNAIC/BENELEARN.

Transfer Learning Across Simulated Robots With Different Sensors pdf

Ann Nowé, Diederik M. Roijers, Hélène Plisnier, 2019, ArXiv.

Dynamic Weights in Multi-Objective Deep Reinforcement Learning

Tom Lenaerts, Ann Nowé, Diederik M. Roijers, 2018, ICML.

MoveRL: To a Safer Robotic Reinforcement Learning Environment

Bram Vanderborght, Ann Nowé, Denis Steckelmacher, 2021, BNAIC/BENELEARN.