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

Introducing the reward: Markov reward process

In our robot example so far, we have not really identified any situation/state that is "good" or "bad." In any system though, there are desired states to be in and there are other states that we want to avoid. In this section, we attach rewards to states/transitions, which gives us a Markov Reward Process (MRP). We then assess the "value" of each state.

Attaching rewards to the grid world example

Remember the version of the robot example where it could not bounce back to the cell it was in when it hits a wall, but crashes in a way that it is not recoverable. From now on, we will work on that version, and attach rewards to the process. Now, let's build this example:

  1. We modify the transition probability matrix to assign self-transition probabilities to the "crashed" state that we add to the matrix:
    P = np.zeros((m2 + 1, m2 + 1))
    P[:m2, :m2] = get_P(3, 0.2, 0.3, 0.25, 0.25)
    for i in...