L'apprentissage profond par renforcement pour soutenir la prise de décision

Deep reinforcement learning to support decision-making in the face of environmental and societal challenges

30 April 2024

Webinar

The next session in the series AI in Life Sciences: young scientists have their say, will be held on Tuesday April 30. Meritxell Vinyals, a young researcher at MIA-T, will explain how she uses deep reinforcement learning to address environmental and societal issues.

Deep reinforcement learning to support decision-making in the face of environmental and societal challenges

by Meritxell Vinyals (MIA-T)

Tuesday 30 April
(webinar)
(14h-15h)

 REGISTER HERE

Résumé : Reinforcement learning (RL) is a branch of machine learning inspired by the way biological entities (e.g. humans, animals) learn. In recent years, we have seen how deep learning has revolutionized machine learning and reinforcement learning is no exception. By leveraging deep neural networks, RL agents have managed to achieve superhuman performance in some long-standing applications. In this talk, I will introduce deep RL and how I use it to respond to some environmental and societal challenges in my ongoing research at INRAE.

Unable to attend previous presentations? Replays are online:

  • Explorer le développement cérébral de l'agneau soumis à différentes expériences précoces grâce à l’IA, par Antoine Bourlier (Doctorant, UMR PRC) >> watch the replay
  • Mieux comprendre les variations d’efficience alimentaire chez le porc grâce à la méthodologie des graphes multicouches, par Camille Juigné (jeune docteure, UMR PEGASE) >> watch the replay
  • Intégration de données multi-omiques grâce aux autoencodeurs variationnels, par Silvia Bottini (Jeune chercheuse, Institut Sophia Agrobiotech) >> watch the replay
  • Modèles de Langage pour l'Extraction d'Informations : Comparaison entre Extraction et Génération de données synthétiques, par Maxime Delmas (post-doc, IDIAP) >> watch the replay

Contact: meritxell.vinyals [AT] inrae.fr

Modification date : 25 March 2024 | Publication date : 25 March 2024