The course focuses on learning methods applicable in situations where knowledge cannot be extracted from an offline dataset but must be obtained through direct field experience using reinforcement learning techniques.
CONTENT
Module 1: Learning from experience – reinforcement learning
How do I learn when I have no supervision?
Learning from experience: reinforcement learning:
• Value-based approaches.
• Policy-based approaches.
• Model-based RL.
• Bandits, Exploration, Exploitation.
Sim-to-real transfer
Behavior cloning and Imitation Learning
Module 2: Intro to practical Reinforcement Learning
Brief recap on Python basics.
Cart-pole benchmark.
OpenAI Gymnasium library.
Random policies and LQR.
Implementation of a RL Agent to control the cartpole.
Reward-shaping.
Training and testing.
COURSE OBJECTIVES
The course aims to address advanced learning topics, providing theoretical knowledge on different supervision strategies and techniques to optimize and strengthen networks.
PREREQUISITES
To fully benefit from this course, it is necessary to possess theoretical and practical knowledge of Artificial Intelligence.