Ects : 2

Enseignant responsable :

• YATING LIU

Volume horaire : 21

Description du contenu de l'enseignement :

• Introduction of Reinforcement Learning
• Multi-armed Bandits problem
• Finite Markov Decision processes
• Dynamic programming
• Sample-based Learning Methods (Monte-Carlo methods, Temporal-difference learning)
• Prediction and Control with Function Approximation

Compétence à acquérir :

• Build a Reinforcement Learning system for sequential decision making. Understand how to formalize your task as a Reinforcement Learning problem, and how to begin implementing a solution.
• Understand RL algorithms (Temporal-Difference learning, Monte Carlo, Q-learning, Policy Gradients etc).

Mode de contrôle des connaissances :

Project