Book Image

Mastering Reinforcement Learning with Python

By : Enes Bilgin
Book Image

Mastering Reinforcement Learning with Python

By: Enes Bilgin

Overview of this book

Reinforcement learning (RL) is a field of artificial intelligence (AI) used for creating self-learning autonomous agents. Building on a strong theoretical foundation, this book takes a practical approach and uses examples inspired by real-world industry problems to teach you about state-of-the-art RL. Starting with bandit problems, Markov decision processes, and dynamic programming, the book provides an in-depth review of the classical RL techniques, such as Monte Carlo methods and temporal-difference learning. After that, you will learn about deep Q-learning, policy gradient algorithms, actor-critic methods, model-based methods, and multi-agent reinforcement learning. Then, you'll be introduced to some of the key approaches behind the most successful RL implementations, such as domain randomization and curiosity-driven learning. As you advance, you’ll explore many novel algorithms with advanced implementations using modern Python libraries such as TensorFlow and Ray’s RLlib package. You’ll also find out how to implement RL in areas such as robotics, supply chain management, marketing, finance, smart cities, and cybersecurity while assessing the trade-offs between different approaches and avoiding common pitfalls. By the end of this book, you’ll have mastered how to train and deploy your own RL agents for solving RL problems.
Table of Contents (24 chapters)
Section 1: Reinforcement Learning Foundations
Section 2: Deep Reinforcement Learning
Section 3: Advanced Topics in RL
Section 4: Applications of RL

ε-greedy actions

An easy to implement, effective and widely used approach to exploration-exploitation problem is what is called ε-greedy actions. This approach suggests, most of the time, greedily taking the action that is the best according to the rewards observed that far in the experiment (i.e. with 1-ε probability); but once in a while (i.e. with ε probability) take a random action regardless of the action performances. Here ε is a number between 0 and 1, usually closer to zero (e.g. 0.1) to "exploit" in most decisions. This way, the method allows continuous exploration of the alternative actions throughout the experiment.

Application to the online advertising scenario

Now, let's implement the ε-greedy actions to the online advertising scenario that we have.

  1. We start with initializing the necessary variables for the experiment, which will keep track of the action value estimates, number of times each ad has been...