Book Image

Hands-On Reinforcement Learning for Games

By : Micheal Lanham
Book Image

Hands-On Reinforcement Learning for Games

By: Micheal Lanham

Overview of this book

With the increased presence of AI in the gaming industry, developers are challenged to create highly responsive and adaptive games by integrating artificial intelligence into their projects. This book is your guide to learning how various reinforcement learning techniques and algorithms play an important role in game development with Python. Starting with the basics, this book will help you build a strong foundation in reinforcement learning for game development. Each chapter will assist you in implementing different reinforcement learning techniques, such as Markov decision processes (MDPs), Q-learning, actor-critic methods, SARSA, and deterministic policy gradient algorithms, to build logical self-learning agents. Learning these techniques will enhance your game development skills and add a variety of features to improve your game agent’s productivity. As you advance, you’ll understand how deep reinforcement learning (DRL) techniques can be used to devise strategies to help agents learn from their actions and build engaging games. By the end of this book, you’ll be ready to apply reinforcement learning techniques to build a variety of projects and contribute to open source applications.
Table of Contents (19 chapters)
1
Section 1: Exploring the Environment
7
Section 2: Exploiting the Knowledge
15
Section 3: Reward Yourself

Exploring Habitat – embodied agents by FAIR

Habitat is a relatively new entry by Facebook AI Research for a new form of embodied agents. This platform represents the ability to represent full 3D worlds displayed from real-world complex scenes. The environment is intended for AI research of robots and robotic-like applications that DRL will likely power in the coming years. To be fair though, pun intended, this environment is implemented to train all forms of AI on this type of environment. The current Habitat repository only features some simple examples and implementation of PPO.

The Habitat platform comes in two pieces: the Habitat Sim and Habitat API. The simulation environment is a full 3D powered world that can render at thousands of frames per second, which is powered by photogrammetry RGBD data. RGBD is essentially RGB color data plus depth. Therefore, any image...