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)

Monte Carlo methods

The Monte Carlo method finds approximate solutions through random sampling, that is, it approximates the probability of an outcome by running multiple trails. It is a statistical technique to find an approximate answer through sampling. Let's better understand Monte Carlo intuitively with an example.

Fun fact: Monte Carlo is named after Stanislaw Ulam's uncle, who often borrowed money from his relatives to gamble in a Monte Carlo casino.

Estimating the value of pi using Monte Carlo

Imagine a quadrant of a circle is placed inside a square, as shown next, and we generate some random points inside the square. You can see that some of the points fall inside the circle while others are outside the...