This repository contains my code and notes from the Udemy course, "Reinforcement Learning: Practical Multi-Armed Bandit Algorithms in Python".
This course provides an introduction to the field of reinforcement learning with a focus on multi-armed bandit problems. The course covers the practical implementation of various algorithmic strategies for balancing between exploration and exploitation. By the end of the course, I was equipped with the knowledge and skills to build and deploy AI agents that can handle critical business operations under uncertainties.
The following topics were covered in this course:
- Introduction to reinforcement learning
- Multi-armed bandit problems
- Epsilon Greedy algorithm
- Softmax Exploration algorithm
- Optimistic Initialization algorithm
- Upper Confidence Bounds (UCB) algorithm
- Thompson Sampling algorithm
- Application of MAB algorithms in robotics using EV3 Mindstorm
I would like to thank the instructor of this course for providing clear and concise explanations of the concepts and algorithms covered. The course materials and code examples were instrumental in my learning of reinforcement learning and multi-armed bandit problems.