Sequential learning
Most of the course is adapted from the course given last year by Emilie Kaufmann (see her page). For information about projects, see here- Lecture 1 - Reinforcement learning
- Lecture 2 - Dynamic programming
- Lecture 3 - Reinforcement learning algorithms
- Practical Session 1 - readme and notebook
- Lecture 4 - Reinforcement learning with function approximation
- Lecture 4.5 - Summary of some points from the first 4 courses
- Lecture 5 - Beyond Value-Based Methods
- Lecture 6 - Stochastic Multi-Armed Bandits
- Lecture 7 - Structured Bandits
- Practical Session 2 - readme and notebook
- Lecture 8 - Bandit Identification
- Practical Session 3 - readme and notebook
- Lecture 9 - Exploration in RL
References
- Bandit Algorithms. Tor Lattimore and Csaba Szepesvari (2019).
- Reinforcement Learning. Richard Sutton and Andrew Barto (2018 edition).
- Reinforcement Learning Algorithms. Csaba Szepesvari (2009).
- Markov Decision Processes. Martin Puterman (1994).
- Lecture notes of similar courses written by several colleagues: Emilie Kaufmann, Rémi Munos, Alessandro Lazaric and Aurélien Garivier.