peer reviewed / The distributional reinforcement learning (RL) approach advocates for representing the complete probability distribution of the random return instead of only modelling its expectation. A distributional RL algorithm may be characterised by two main components, namely the representation of the distribution together with its parameteri...
7. Affordable and clean energy / 13. Climate action / 9. Industry, innovation and infrastructure
peer reviewed / This article presents the evaluation of a bespoke machine translation (MT) system adapted to the work of a literary translator who specializes in fiction. Actualizing a research avenue for the English–French pair and complementing a growing number of studies for other language combinations, our work on literary machine translation s...
peer reviewed / This paper focuses on a programming methodology relying on an informal and graphical version of the \invariant for building the code. This methodology is applied in the context of a CS1 course in which students are exposed to several C programming language concepts and algorithmic aspects. The key point in the course is thus to imag...
SoccerNet is a large-scale video dataset for video undestanding in soccer. The dataset has been used in various research challenges, where participants competed to develop the best algorithms for tasks such as predicting events, tracking players or recognising their jersey number. The challenges have spurred advancements in the state-of-the-art in ...
peer reviewed / The control of Renewable Energy Communities (REC) with controllable assets (e.g batteries) can be formalised as an optimal control problem. This paper proposes a generic formulation for such a problem whereby the electricity generated by the community members is redistributed using repartition keys. These keys represent the fraction...
This course provides an introduction to the essential role of mathematical optimization in the sizing and operation of energy systems. After a theoretical overview of the concepts, participants will be presented with the GBOML modeling tool, a graph-oriented tool for dealing with these problems. This course is divided into four parts: firstly, we e...
peer reviewed / Personalized support and assistance are essential for cancer survivors, given the physical and psychological consequences they have to suffer after all the treatments and conditions associated with this illness. Digital assistive technologies have proved to be effective in enhancing the quality of life of cancer survivors, for insta...
Polynomial unconstrained optimization problems in binary variables (PUBO) are notoriously hard to solve. This talk presents an overview of recent advances which are revisiting ideas introduced more than 50 years ago. A first idea consists in solving the PUBO problem by dynamic programming techniques which eliminate variables one by one, iteratively...
We experimentally demonstrate that an uncertainty-aware framework for robotic navigation and vision is able to navigate a robotic platform around an obstacle without choosing an overly long and conservative path. The framework contains many interconnected experimental pieces, including monocular visual-inertial odometry (VIO) based on an Extended K...
