REINFORCEMENT LEARNING
REINFORCEMENT LEARNING
This is a course on the foundamental concepts, algorithms and techniques for Reinforcement Learning. It is about learning the optimal behavior in an environment to obtain maximum reward. This optimal behavior is learned through interactions with the environment and observations of how it responds, similar to children exploring the world around them and learning the actions that help them achieve a goal. From Dynamic Programming to Model Free prediction and control algorithms. Function approximation, policy gradient and deep reinforcement learning.
- In collaboration with: Giovanni Stilo & Andrea D'Angelo (Università degli Studi dell'Aquila), Roberto Trasarti (CNR-ISTI)
- Estimated time: ≈ 2.30h