Welcome to the MAB repository. The Multi-Armed Bandit problem is a classic example of decision-making under uncertainty, often encountered in reinforcement learning, optimization, and many other fields. This repo contains the theory and some implementations of various classic MAB algorithms such as
/algorithms- Contains implementation of various MAB algorithms in Python./slides- Contains presentation slides for each topic./theory- Includes theoretical explanations and derivations related to MAB problems and algorithms./project- Capstone project.