Reinforcement Learning
Bordeaux INP, A3 IA
- Course Slides
- Prsentation pdf
- Basic Concepts pdf
- Multi-armed bandits pdf
- Markov Decision Processes pdf
- Bellman's Equations and Dynamic Programmingpdf
- Model-free Methodes:
- Monte Carlo Method pdf
- Temporal Difference Learning (TD, SARSA, Q-Learning) pdf
- Appriximation Methodes:
- Monte-Carlo Tree Search pdf
- Deep Q-Learning pdf
- Multi-Agent RL (An Introduction) pdf
- Hands-On
- (Minis) Projects
- To be submitted by 12/08/2024 at 11:59 PM at the latest: Implement the Model-free methods on grid_world.py
Attention : You are not allowed to modify the code in the grid_world.py file.
- Project
- Project description pdf
- Project to be submitted by 05/01/2025 at 11:59 PM at the latest.