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 MC control with epsilon-greedy policy

In the previous recipe, we searched for the optimal policy using MC control with greedy search where the action with the highest state-action value was selected. However, the best choice available in early episodes does not guarantee an optimal solution. If we just focus on what is temporarily the best option and ignore the overall problem, we will be stuck in local optima instead of reaching the global optima. The workaround is epsilon-greedy policy.

In MC control with epsilon-greedy policy, we no longer exploit the best action all the time, but choose an action randomly under certain probabilities. As the name implies, the algorithm has two folds:

  • Epsilon: given a parameter, ε, with a value from 0 to 1, each action is taken with a probability calculated as follows:

Here, |A| is the number of possible actions.

  • Greedy...