Renforcement Learning

Ects : 2

Enseignant responsable :

Volume horaire : 21

Description du contenu de l'enseignement :

1/ Introduction to reinforcement learning 2/ Theoretical formalism: Markov Decision Processes (MDPs), value function (Bellman equation and Hamilton–Jacobi–Bellman equation), etc. 3/ Common strategies illustrated with the “multi-armed bandit” example 4/ Deep learning strategies: Q-learning, DQN 5/ Deep learning strategies: SARSA and variants 6/ Deep learning strategies: Actor–Critic and variants 7/ Various Python implementations 8/ Ethical perspectives, the alignment problem, recent approaches and applications

Pré-requis recommandés :

tensorflow, keras, pytorch

Pré-requis obligatoires :

python, numérical analysis

Compétence à acquérir :

Introduction to reinforcement learning and deep reinforcement learning, with an empirical machine learning perspective: main algorithms, practical implementations (gymnasium)

Bibliographie, lectures recommandées

turinici.com

En savoir plus sur le cours