Reinforcement Learning
D. BASU, E. KAUFMANN, O. MAILLARD
Deep LearningLearning

Objectif du cours

This class aims at providing a comprehensive and modern introduction to reinforcement learning concepts and algorithms. It endeavors to provide a solid formal basis on foundational notions of reinforcement learning.

Organisation des séances

8 lectures + 1 written exam

Lecture 1 : MDP and Dynamic Programming
Lecture 2 : The first algorithms of Reinforcement Learning
Lecture 3 : The Actors : Policy Iteration and Gradient
Lecture 4 : The Critics : RL with functiun Approximation
Lecture 5 : Scaling up RL : Towards Deep RL and Continuous MDPS
Lecture 6 : Exploration-Exploitation in RL
Lecture 7 : Average-reward Reinforcement Learning and Instance Optimal Algorithms
Lecture 8 : Bandit Methods for Pure Exploration and Planning in RL

Mode de validation

1 written exam (after class 8) and 1 programming assignment (after class 5)

Les intervenants

Debabrota BASU

INRIA

Émilie KAUFMANN

INRIA, Université de Lille

Odalric MAILLARD

INRIA

voir les autres cours du 2nd semestre