222 citations · 600 across the 46 of their papers we have counts for
6 papers · 1 filter
IMP-MARL: a Suite of Environments for Large-scale Infrastructure Management Planning via MARL
Pascal Leroy, Pablo G. Morato, Jonathan Pisane +2
We introduce IMP-MARL, an open-source suite of multi-agent reinforcement learning (MARL) environments for large-scale Infrastructure Management Planning (IMP), offering a platform…
Informed POMDP: Leveraging Additional Information in Model-Based RL
Gaspard Lambrechts, Adrien Bolland, Damien Ernst
In this work, we generalize the problem of learning through interaction in a POMDP by accounting for eventual additional information available at training time. First, we introduce…
Spike-based computation using classical recurrent neural networks
Florent De Geeter, Damien Ernst, Guillaume Drion
Spiking neural networks are a type of artificial neural networks in which communication between neurons is only made of events, also called spikes. This property allows neural netw…
Policy Gradient Algorithms Implicitly Optimize by Continuation
Adrien Bolland, Gilles Louppe, Damien Ernst
Direct policy optimization in reinforcement learning is usually solved with policy-gradient algorithms, which optimize policy parameters via stochastic gradient ascent. This paper…
Multi-objective near-optimal necessary conditions for multi-sectoral planning
Antoine Dubois, Jonathan Dumas, Paolo Thiran +2
This paper extends the concepts of epsilon-optimal spaces and necessary conditions for near-optimality from single-objective to multi-objective optimisation. These notions are firs…
Matching of Everyday Power Supply and Demand with Dynamic Pricing: Problem Formalisation and Conceptual Analysis
Thibaut Théate, Antonio Sutera, Damien Ernst
The energy transition is expected to significantly increase the share of renewable energy sources whose production is intermittent in the electricity mix. Apart from key benefits,…