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)

Solving internet advertising problems with a multi-armed bandit

Imagine you are an advertiser working on ad optimization on a website:

  • There are three different colors of ad background – red, green, and blue. Which one will achieve the best click-through rate (CTR)?
  • There are three types of wordings of the ad – learn …, free ..., and try .... Which one will achieve the best CTR?

For each visitor, we need to choose an ad in order to maximize the CTR over time. How can we solve this?

Perhaps you are thinking about A/B testing, where you randomly split the traffic into groups and assign each ad to a different group, and then choose the ad from the group with the highest CTR after a period of observation. However, this is basically a complete exploration, and we are usually unsure of how long the observation period should be and will end up losing a large portion...