Book Image

PyTorch 1.x Reinforcement Learning Cookbook

By : Yuxi (Hayden) Liu
Book Image

PyTorch 1.x Reinforcement Learning Cookbook

By: Yuxi (Hayden) Liu

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)

Performing Monte Carlo policy evaluation

In Chapter 2, Markov Decision Process and Dynamic Programming, we applied DP to perform policy evaluation, which is the value (or state-value) function of a policy. It works really well, but has some limitations. Fundamentally, it requires a fully known environment, including the transition matrix and reward matrix. However, the transition matrix in most real-life situations is not known beforehand. A reinforcement learning algorithm that needs a known MDP is categorized as a model-based algorithm. On the other hand, one with no requirement of prior knowledge of transitions and rewards is called a model-free algorithm. Monte Carlo-based reinforcement learning is a model-free approach.

In this recipe, we will evaluate the value function using the Monte Carlo method. We will use the FrozenLake environment again as an example, assuming we...