#### Overview of this book

Reinforcement learning (RL) is a branch of machine learning that has gained popularity in recent times. It allows you to train AI models that learn from their own actions and optimize their behavior. PyTorch has also emerged as the preferred tool for training RL models because of its efficiency and ease of use. With this book, you'll explore the important RL concepts and the implementation of algorithms in PyTorch 1.x. The recipes in the book, along with real-world examples, will help you master various RL techniques, such as dynamic programming, Monte Carlo simulations, temporal difference, and Q-learning. You'll also gain insights into industry-specific applications of these techniques. Later chapters will guide you through solving problems such as the multi-armed bandit problem and the cartpole problem using the multi-armed bandit algorithm and function approximation. You'll also learn how to use Deep Q-Networks to complete Atari games, along with how to effectively implement policy gradients. Finally, you'll discover how RL techniques are applied to Blackjack, Gridworld environments, internet advertising, and the Flappy Bird game. By the end of this book, you'll have developed the skills you need to implement popular RL algorithms and use RL techniques to solve real-world problems.
Table of Contents (11 chapters)
Preface
Free Chapter
Getting Started with Reinforcement Learning and PyTorch
Markov Decision Processes and Dynamic Programming
Monte Carlo Methods for Making Numerical Estimations
Capstone Project – Playing Flappy Bird with DQN
Other Books You May Enjoy

# Monte Carlo Methods for Making Numerical Estimations

In the previous chapter, we evaluated and solved a Markov Decision Process (MDP) using dynamic programming (DP). Model-based methods such as DP have some drawbacks. They require the environment to be fully known, including the transition matrix and reward matrix. They also have limited scalability, especially for environments with plenty of states.

In this chapter, we will continue our learning journey with a model-free approach, the Monte Carlo (MC) methods, which have no requirement of prior knowledge of the environment and are much more scalable than DP. We will start by estimating the value of Pi with the Monte Carlo method. Moving on, we will talk about how to use the MC method to predict state values and state-action values in a first-visit and every-visit manner. We will demonstrate training an agent to play the Blackjack...