Introduction to MDP and RL 2026-2027 (IMRL)

Table of Contents

marvin image

Syllabus

We will focus on the formalization of decision making for a robotic agent. What strategy should it implement to solve a complex problem with unknown and/or random events? We will use as our main formalism reinforcement learning.

This lecture consists of an introduction and 6 classes. Each class presents a new notion and is followed by a lab session where students are required to implement the new notion to check their understanding. Every lab session starts by a 10-minute quiz, on material presented the weeks before.


IMRL Introduction 01/09/2026

Lecture

Introduction and Markov Decision Processes (part 1)

  • Introduction to decision problem for autonomous agents
  • Markov Decision Processes (MDP)
    • The agent-environment model
    • Introduction to MDP
    • Policy and Decision making
    • Concepts: Gains, State Values, State-Action Values

References


IMRL Session 1 04/09/2026

Lecture

Markov Decision Processes (part 2) + introduction Monte Carlo methods and temporal difference methods

  • Markov Decision processes (MDP)
    • Optimal (decision) policy
    • gain, state values, state-action values
    • optimal policy by policy iteration
    • optimal policy by value iteration

Lab Session

Introduction python/pytorch/colab: link to lab page if you don't know python

How to get a Frisbee on a frozen lake? link to lab page (1st part)

References


IMRL Session 2 11/09/2026

Lecture

Monte Carlo methods and temporal difference methods

  • Markov Decision Process (MDP) recap
  • Monte-Carlo method
  • Temporal Difference methods
  • Learning \(Q\) table with Q-learning and SARSA

Lab Session

How to get a Frisbee on a frozen lake? link to lab page (2nd part)

References

IMRL Session 3 18/09/2026

Lab Session

Mountain Car and tabular SARSA/Q-Learning link to lab page

References


IMRL Session 4 25/09/2026

Lecture

Function approximation and input encoding

  • input encoding and features extraction
  • introduction to neural networks

Lab Session

Mountain Car with function and one-hot encoding link to lab page

References


IMRL Session 5 02/10/2026

Lecture

Direct policy learning : policy gradient algorithm

policy learning

Lab Session

Mountain Car by function with tile coding link to lab page


IMRL Session 6 09/10/2026

Lecture

Follow-up Direct policy learning : policy gradient algorithm and actor/critic policy learning

Lab Session

Lunar Lander link to page


IMRL Exam 16/10/2026 10:00-12:00

Only Annotated handouts authorized

General References

Slides for annotation

Author: Joseph Le Roux

Created: 2026-07-16 jeu. 08:05