CentraleSupélec | Etienne Chassaing

Reinforcement Learning

Mon, 01 Jan 0001 00:00:00 +0000

An introductory course on Reinforcement Learning, structured as four lectures, each followed by a tutorial.

Lectures

Lecture 1: Introduction and MDPs open ↗

Lecture 2: Dynamic Programming open ↗

Lecture 3: Model-Free Prediction open ↗

Lecture 4: Model-Free Control & Deep RL Applications open ↗

Session 1: Markov decision processes, return, value functions, Bellman equations.
Session 2: policy evaluation, policy iteration, value iteration.
Session 3: Monte-Carlo methods, temporal differences TD(0).
Session 4: Monte-Carlo control, SARSA, Q-learning, and a look at deep RL.

Written exercises

Exercises: Introduction and MDPs open ↗

Exercises: Dynamic Programming open ↗

Exercise sheets for sessions 3 and 4, and the notebook tutorials, are in preparation.

See also the Deep Reinforcement Learning training I delivered in companies: same fundamentals, geared towards hands-on practice with Stable-Baselines3 and Gym.

Robotics elective

Mon, 01 Jan 0001 00:00:00 +0000

I am designing the CentraleSupélec elective Robotics Systems, from Motion to Embodied AI, taught from April 2027.

It will cover kinematics, dynamic modelling, trajectory planning and torque control; then biomimetic versus learned locomotion, learning and formal guarantees; and ends with a Python project in MuJoCo.

The course material will be published here once the course has started.

Robotics project supervision

Thu, 01 Jan 2026 00:00:00 +0000

Robotics project - CentraleSupélec

Summary

Since January 2026, I supervise robotics projects for CentraleSupélec students.