Emploi
Mes offres
Mes alertes emploi
Se connecter
Trouver un emploi Astuces emploi Fiches entreprises
Chercher

Internship opportunity: development of explainable reinforcement learning methods for various applications

Mons
Stage
Multitel asbl
Publiée le 18 novembre
Description de l'offre

Reinforcement Learning Reinforcement learning (RL) is an emerging field in AI where an agent has to learn to behave optimally in its environment. It learns by taking successive decisions, aka actions, and receiving feedback under the form of a numerical reward that must be maximized over a series of steps. The difference with a more standard use of supervised learning AI is that the agent creates his training data himself, by picking actions, experiencing their effect on the environment, and by observing which state he ends up in. EXplainable AI and eXplainable RL (XRL) EXplainable AI (XAI) is the field of research that focuses on making AI systems and their decision-making processes more understandable to humans. It aims to create AI models that not only perform tasks but also provide explanations for their actions and predictions, fostering trust and facilitating human oversight. EXplainable Reinforcement Learning (XRL) applies the same idea for RL agents. Multitel At Multitel we have various projects using RL in a broad spectrum of fields, such as automation in defense, scheduling optimization in production chains or laser control in decoating applications. Most of these applications should benefit from adding an XRL brick and the recently released AI act dictates a mandatory XAI/XRL add-on to any AI product in critical fields (healthcare, defense, ). The Internship This internship will explore cutting-edge solutions in XRL. The main goal of this internship is to find which XRL methods are best suited for Multitel RL projects and how can they be applied to produce explainability elements. In particular, we are interested in intrinsic XAI methods such as saliency maps. The chosen methods will be tested in simplified environments so that the candidate will be able to play with various RL agents him/herself and develop his/her own skills in this area. Expected qualifications: A strong interest in AI, proficiency in Python and Pytorch, basic knowledge of Git for version control, a curious and autonomous mindset. Duration: from 3 to 6 months CV and cover letter requiered You will work in a dynamic and welcoming environment. You’ll be part of a friendly and energetic team. We offer a stimulating and supportive work environment. Recognized as a centre of excellence at the international level, Multitel develops and integrates emerging technologies in the industrial sector. These technologies are focused on five main areas of activity: Networks and Cybersecurity, Applied Photonics, Artificial Intelligence, Embedded Systems, and Railway Certification Within the Artificial Intelligence department, the AI team holds a crucial role in supporting companies with their technological innovation projects, guiding them from the feasibility phase to the minimum viable product in various application fields such as aerospace, automotive, Smart Cities, Industry 4.0, medical sciences, defense, and more. We love fresh ideas, shared coffees, and motivated people. If you’re eager to learn fast and make a real impact, join us!

Postuler
Créer une alerte
Alerte activée
Sauvegardée
Sauvegarder
Offres similaires
Emploi Mons
Emploi Hainaut
Emploi Région Wallonne
Accueil > Emploi > Internship Opportunity: Development of Explainable Reinforcement Learning Methods for Various Applications

Jobijoba

  • Dossiers emploi
  • Avis Entreprise

Trouvez des offres

  • Offres d'emploi par métier
  • Recherche d'emploi par secteur
  • Emplois par sociétés
  • Emploi par localité

Contact / Partenariats

  • Contact
  • Publiez vos offres sur Jobijoba

Mentions légales - Conditions générales d'utilisation - Politique de confidentialité - Gérer mes cookies - Accessibilité : Non conforme

© 2025 Jobijoba - Tous Droits Réservés

Postuler
Créer une alerte
Alerte activée
Sauvegardée
Sauvegarder