#### Overview of this book

Various intelligent applications such as video games, inventory management software, warehouse robots, and translation tools use reinforcement learning (RL) to make decisions and perform actions that maximize the probability of the desired outcome. This book will help you to get to grips with the techniques and the algorithms for implementing RL in your machine learning models. Starting with an introduction to RL, youÔÇÖll be guided through different RL environments and frameworks. YouÔÇÖll learn how to implement your own custom environments and use OpenAI baselines to run RL algorithms. Once youÔÇÖve explored classic RL techniques such as Dynamic Programming, Monte Carlo, and TD Learning, youÔÇÖll understand when to apply the different deep learning methods in RL and advance to deep Q-learning. The book will even help you understand the different stages of machine-based problem-solving by using DARQN on a popular video game Breakout. Finally, youÔÇÖll find out when to use a policy-based method to tackle an RL problem. By the end of The Reinforcement Learning Workshop, youÔÇÖll be equipped with the knowledge and skills needed to solve challenging problems using reinforcement learning.
Preface
1. Introduction to Reinforcement Learning
Free Chapter
2. Markov Decision Processes and Bellman Equations
3. Deep Learning in Practice with TensorFlow 2
4. Getting Started with OpenAI and TensorFlow for Reinforcement Learning
5. Dynamic Programming
6. Monte Carlo Methods
7. Temporal Difference Learning
8. The Multi-Armed Bandit Problem
9. What Is Deep Q-Learning?
10. Playing an Atari Game with Deep Recurrent Q-Networks
11. Policy-Based Methods for Reinforcement Learning
12. Evolutionary Strategies for RL

# Formulation of the MAB Problem

In its most simple form, the MAB problem consists of multiple slot machines (casino gambling machines), each of which can return a stochastic reward to the player each time it is played (specifically, when its arm is pulled). The player, who would like to maximize their total reward at the end of a fixed number of rounds, does not know the probability distribution or the average reward that they will obtain from each slot machine. The problem, therefore, boils down to the design of a learning strategy where the player needs to explore what possible reward values each slot machine can return and from there, quickly identify the one that is most likely to return the greatest expected reward.

In this section, we will briefly explore the background of the problem and establish the notation and terminology that we will be using throughout this chapter.

## Applications of the MAB Problem

The slot machines we mentioned earlier are just a simplification...