Module 02: Multi-Armed Bandits & Exploration

Coming soon.

The simplest RL setting - and the best place to build intuition for the exploration vs exploitation tradeoff.

Learning Objectives

• Understand the multi-armed bandit problem
• Implement epsilon-greedy, UCB, and Thompson Sampling
• Analyze regret bounds and sample complexity
• Bridge from bandits to contextual bandits and full RL

Concept Explanation

Coming soon.

Code Examples

Coming soon.

Exercises

Coming soon.