Descriptif
Content: This course is a math oriented introduction to Reinforcement Learning. The goal is to present the foundations of Reinforcement Learning in order for the students to be able to read and implement research articles. An emphasis will be made on the underlying math as it eases to understand the algorithm heuristics.
Grading: Project based on a research article (theoretical study and/or implementation)
21 heures en présentiel
Diplôme(s) concerné(s)
Format des notes
Numérique sur 20Littérale/grade réduitPour les étudiants du diplôme M2 MSV - Mathématiques pour les Sciences du Vivant
L'UE est acquise si Note finale >= 10- Crédits ECTS acquis : 3 ECTS
Pour les étudiants du diplôme M2 DS - Data Science
Le rattrapage est autorisé (Max entre les deux notes)- Crédits ECTS acquis : 3 ECTS
Programme détaillé
Syllabus:
- Sequential Decisions, MDP and Policies
- Operations Research: Prediction and Planning
- Reinforcement Learning: Prediction and Planning in the Tabular Setting
- Reinforcement Learning: Advanced Techniques in the Tabular Setting
- Reinforcement Learning: Approximation of the Value Functions
- Reinforcement Learning: Policy Approach
