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)

Developing the Double Q-learning algorithm

In this is a bonus recipe, in this chapter where we will develop the double Q-learning algorithm.

Q-learning is a powerful and popular TD control reinforcement learning algorithm. However, it may perform poorly in some cases, mainly because of the greedy component, maxa'Q(s', a'). It can overestimate action values and result in poor performance. Double Q-learning was invented to overcome this by utilizing two Q functions. We denote two Q functions as Q1 and Q2. In each step, one Q function is randomly selected to be updated. If Q1 is selected, Q1 is updated as follows:

If Q2 is selected, it is updated as follows:

This means that each Q function is updated from another one following the greedy search, which reduces the overestimation of action values using a single Q function.