Despite achieving impressive performances on various tasks, modern artificial intelligence (AI) systems have become complex black box models. A growing body of work aspires to open the box and understand its internal functioning. In this new article (Lambrechts et al., 2022), we follow this field of research by studying the internal representation that intelligent agents learn through reinforcement learning (RL), when those agents act in partially observable environments (POEs). In particular, the informational content of the memory of those agents is studied when the latter are trained to act optimally in maze and orientation tasks.

The decarbonisation of energy systems is one of the main challenges of our century. Finding the optimal technological mix to achieve that goal is a major concern for policy and decision makers alike. These problems [...]

The research positions are about combining modelling, simulation, optimisation, and machine learning techniques in order to investigate several technical, economic and regulatory aspects induced by major upcoming changes in energy (and in particular, electricity) generation, [...]

Download the paper Summary: Active network management (ANM) of electricity distribution networks include many complex stochastic sequential optimization problems. These problems need to be solved for integrating renewable energies and distributed storage into future electrical [...]

Decarbonising sectors such as aviation, heating and industry has proved difficult via direct electrification. Hence, the synthesis of carbon-neutral fuels and feedstocks from renewable electricity has received much attention in recent years. However, in European [...]