59 citations · 72 across the 14 of their papers we have counts for
14 papers
Critic-Driven Voronoi-Quantization for Distilling Deep RL Policies to Explainable Models
Senne Deproost, Denis Steckelmacher, Ann Nowé
Despite many successful attempts at explaining Deep Reinforcement Learning policies using distillation, it remains difficult to balance the performance-interpretability trade-off a…
Optimistic Reinforcement Learning-Based Skill Insertions for Task and Motion Planning
Gaoyuan Liu, Joris de Winter, Yuri Durodie +3
Task and motion planning (TAMP) for robotics manipulation necessitates long-horizon reasoning involving versatile actions and skills. While deterministic actions can be crafted by…
A Task-Efficient Reinforcement Learning Task-Motion Planner for Safe Human-Robot Cooperation
Gaoyuan Liu, Joris de Winter, Kelly Merckaert +3
In a Human-Robot Cooperation (HRC) environment, safety and efficiency are the two core properties to evaluate robot performance. However, safety mechanisms usually hinder task effi…
Human-Readable Programs as Actors of Reinforcement Learning Agents Using Critic-Moderated Evolution
Senne Deproost, Denis Steckelmacher, Ann Nowé
With Deep Reinforcement Learning (DRL) being increasingly considered for the control of real-world systems, the lack of transparency of the neural network at the core of RL becomes…
Dynamic Size Message Scheduling for Multi-Agent Communication under Limited Bandwidth
Qingshuang Sun, Denis Steckelmacher, Yuan Yao +2
Communication plays a vital role in multi-agent systems, fostering collaboration and coordination. However, in real-world scenarios where communication is bandwidth-limited, existi…
Transferring Multiple Policies to Hotstart Reinforcement Learning in an Air Compressor Management Problem
Hélène Plisnier, Denis Steckelmacher, Jeroen Willems +2
Many instances of similar or almost-identical industrial machines or tools are often deployed at once, or in quick succession. For instance, a particular model of air compressor ma…
Synthesising Reinforcement Learning Policies through Set-Valued Inductive Rule Learning
Youri Coppens, Denis Steckelmacher, Catholijn M. Jonker +1
Today's advanced Reinforcement Learning algorithms produce black-box policies, that are often difficult to interpret and trust for a person. We introduce a policy distilling algori…
Transfer Learning Across Simulated Robots With Different Sensors
Hélène Plisnier, Denis Steckelmacher, Diederik Roijers +1
For a robot to learn a good policy, it often requires expensive equipment (such as sophisticated sensors) and a prepared training environment conducive to learning. However, it is…
Sample-Efficient Model-Free Reinforcement Learning with Off-Policy Critics
Denis Steckelmacher, Hélène Plisnier, Diederik M. Roijers +1
Value-based reinforcement-learning algorithms provide state-of-the-art results in model-free discrete-action settings, and tend to outperform actor-critic algorithms. We argue that…
The Actor-Advisor: Policy Gradient With Off-Policy Advice
Hélène Plisnier, Denis Steckelmacher, Diederik M. Roijers +1
Actor-critic algorithms learn an explicit policy (actor), and an accompanying value function (critic). The actor performs actions in the environment, while the critic evaluates the…
Dynamic Weights in Multi-Objective Deep Reinforcement Learning
Axel Abels, Diederik M. Roijers, Tom Lenaerts +2
Many real-world decision problems are characterized by multiple conflicting objectives which must be balanced based on their relative importance. In the dynamic weights setting the…
Directed Policy Gradient for Safe Reinforcement Learning with Human Advice
Hélène Plisnier, Denis Steckelmacher, Tim Brys +2
Many currently deployed Reinforcement Learning agents work in an environment shared with humans, be them co-workers, users or clients. It is desirable that these agents adjust to p…
Reinforcement Learning in POMDPs with Memoryless Options and Option-Observation Initiation Sets
Denis Steckelmacher, Diederik M. Roijers, Anna Harutyunyan +3
Many real-world reinforcement learning problems have a hierarchical nature, and often exhibit some degree of partial observability. While hierarchy and partial observability are us…
An Empirical Comparison of Neural Architectures for Reinforcement Learning in Partially Observable Environments
Denis Steckelmacher, Peter Vrancx
This paper explores the performance of fitted neural Q iteration for reinforcement learning in several partially observable environments, using three recurrent neural network archi…