11: Reinforcement Learning

Date: 31st January 2024

💡 This week's focus will be on exploring Reinforcement Learning (RL), a domain that enables the creation of AI agents capable of learning autonomously. In contrast to supervised learning, where learning occurs through pre-defined correct examples, RL empowers agents to learn from their own experiences via a trial-and-error approach. We'll begin with an introduction to bandit algorithms, which are foundational to online advertising and recommendation systems. Following this, we'll delve into more advanced algorithms like Q-learning, which are instrumental in training robots for autonomous operations and navigating self-driving cars. 💡

You can access our slides here: 💻 Tutorial 11 Slides