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

Exploration-Exploitation Trade-Off

As we mentioned earlier, RL is all about learning from experience without a supervisor labeling correct actions for the agent. The agent observes the consequences of its actions, identifies what actions are leading to the highest rewards in each situation and learns from this experience. Now, think about something you learned from your own experience. For example, how to study for a test. Chances are you explored different methods until you discovered what works the best for you. Maybe you studied regularly for your tests first, but then you tried whether studying the last night before the test could work well enough - and maybe it does for certain types of tests. The point is that you had to explore to find the method(s) that maximizes your "reward," which is a function of your test score, time spent for leisure activities, your anxiety levels before and during the test etc. In fact, exploration is essential for any learning that is...