What this book covers

Chapter 1, Overview of Keras Reinforcement Learning, will get you ready to enjoy reinforcement learning using Keras, looking at topics ranging from the basic concepts right to the building of models. By the end of this chapter, you will be ready to dive into working on real-world projects.

Chapter 2, Simulating Random Walks, will have you simulate a random walk using Markov chains through a Python code implementation.

Chapter 3, Optimal Portfolio Selection, explores how to select the optimal portfolio using dynamic programming through a Python code implementation.

Chapter 4, Forecasting Stock Market Prices, guides you in using the Monte Carlo methods to forecast stock market prices.

Chapter 5, Delivery Vehicle Routing Application, shows how to use Temporal Difference (TD) learning algorithms to manage warehouse operations through Python and the Keras library.

Chapter 6, Continuous Balancing of a Rotating Mechanical System, helps you to use deep reinforcement learning methods to balance a rotating mechanical system.

Chapter 7, Dynamic Modeling of a Segway as an Inverted Pendulum System, teaches you the basic concepts of Q-learning and how to use this technique to control a mechanical system.

Chapter 8, A Robot Control System Using Deep Reinforcement Learning, will confront you with the problem of robot navigation in simple maze-like environments where the robot has to rely on its on-board sensors to perform navigation tasks.

Chapter 9, Handwritten Digit Recognizer, shows how to set up a handwritten digit recognition model in Python using an image dataset.

Chapter 10, Playing the Board Game Go, explores how reinforcement learning algorithms were used to address a problem in game theory.

Chapter 11, What's Next?, gives a good understanding of the real-life challenges in building and deploying machine learning models, and explores additional resources and technologies that will help sharpen your machine learning skills.