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

Need for policy-based methods

We start this chapter by first discussing why we need policy-based methods as we have already introduced many value-based methods. Policy-based methods i) are arguably more principled as they directly optimize the policy parameters, ii) allow us to use continuous action spaces, and iii) are able to learn truly random stochastic policies. Let's now go into the details of each of these points.

A more principled approach

In Q-learning, a policy is obtained in an indirect manner by learning action values, which are then used to determine the best action(s). But do we really need to know the value of an action? Most of the time we don't, as they are only proxies to get us to optimal policies. Policy-based methods learn function approximations that directly give policies without such an intermediate step. This is arguably a more principled approach because we can take gradient steps directly to optimize the policy, not the proxy action-value...