This book is your one-stop shop for learning how various reinforcement learning (RL) techniques and algorithms play an important role in game development using Python.
The book will start with the basics to provide you with the necessary foundation to understand how RL is playing a major role in game development. Each chapter will help you implement various RL techniques, such as Markov decision processes, Q-learning, the actor-critic method, state-action-reward-state-action (SARSA), and the deterministic policy gradients algorithm, to build logical self-learning agents. You will use these techniques to enhance your game development skills and add various features to improve your overall productivity. Later in the book, you will learn how deep RL techniques can be used to devise strategies that enable agents to learn from their own actions so that you can build fun and engaging games.
By the end of the book, you will be able to use RL techniques to build various projects and contribute to open source applications.
