Department of Mathematics and Statistics
University of Jyväskylä
34th Jyväskylä Summer School

MA1: Machine Learning and Stochastic Control
Huyên Pham (Ecole Polytechnique, France)

Abstract

• I. Foundations of Machine learning and stochastic control
  • 1. Introduction/motivation
  • 2. Basics of Markov decision process (MDP) and Reinforcement learning (RL)
• II. Deep learning for stochastic control and PDEs
  1. Neural networks algorithms for MDP
  • 2. Deep Galerkin, Physics-Informed neural networks
  • 3. Deep backward SDE
  • 4. Deep backward dynamic programming
• III. Reinforcement learning methods in continuous time
  • 1. Exploratory formulation of RL
  • 2. Policy gradient methods and actor/critic algorithms
  • 3. q-learning and approximation in continuous time

Coordinates

• 04.08.2025 - 08.08.2025 (Monday - Friday)
• 12:00-14:00
• Lecture hall: MaD 202
  • Use the map or contact the organizers if you have difficulties finding the room.

Teaching material

• Lecture 1
• Lecture 2
• Lecture 3
• Lecture 4
• Lecture 5

Supplementary teaching material

• Lecture notes about stochastic differential equations and stochastic processes

Organization

• Coordinator: Stefan Geiss
• Lecturing room: MaD202
• In case of questions, please contact Irfan Durmic or Stefan Geiss.

Passing the course

Useful information

• Restaurant menus
• MyJYU app
• Social programme