Book Image

Hands-On Reinforcement Learning with Python

By : Sudharsan Ravichandiran
Book Image

Hands-On Reinforcement Learning with Python

By: Sudharsan Ravichandiran

Overview of this book

Reinforcement Learning (RL) is the trending and most promising branch of artificial intelligence. Hands-On Reinforcement learning with Python will help you master not only the basic reinforcement learning algorithms but also the advanced deep reinforcement learning algorithms. The book starts with an introduction to Reinforcement Learning followed by OpenAI Gym, and TensorFlow. You will then explore various RL algorithms and concepts, such as Markov Decision Process, Monte Carlo methods, and dynamic programming, including value and policy iteration. This example-rich guide will introduce you to deep reinforcement learning algorithms, such as Dueling DQN, DRQN, A3C, PPO, and TRPO. You will also learn about imagination-augmented agents, learning from human preference, DQfD, HER, and many more of the recent advancements in reinforcement learning. By the end of the book, you will have all the knowledge and experience needed to implement reinforcement learning and deep reinforcement learning in your projects, and you will be all set to enter the world of artificial intelligence.
Table of Contents (16 chapters)

Applications of MAB

So far, we have looked at the MAB problem and how we can solve it using various exploration strategies. But bandits are not just used for playing slot machines; they have many applications.

Bandits are used as a replacement for AB testing. AB testing is one of the commonly used classical methods of testing. Say you have two versions of the landing page of your website. How do you know which version is liked by most of the users? You conduct an AB test to understand which version is most liked by users.

In AB testing, we allocate a separate time for exploration and a separate time for exploitation. That is, it has two different dedicated periods only for exploration and exploitation alone. But the problem with this method is that this will incur a lot of regrets. So, we can minimize the regret using various exploration strategies that we use to solve MAB. Instead...