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

Action selection using upper confidence bounds

Upper confidence bounds (UCB) is a simple yet effective solution to exploration-exploitation trade-off. The idea is that at each time step, we select the action that has the highest potential for reward. The potential of the action is calculated as the sum of the action value estimate and a measure of the uncertainty of this estimate. This sum is what we call the upper confidence bound. So, an action is selected either because our estimate for the action value is high, or the action has not been explored enough (i.e. as many times as the other ones) and there is high uncertainty about its value, or both.

More formally, we select the action to take at time using:

Let's unpack this a little bit:

  • Now we have used a notation that is slightly different from what we introduced earlier.  and have essentially the same meanings as before. This formula looks at the variable values, which may have...