Deep learning is the evolution of raw computational learning and it is quickly evolving and starting to dominate all areas of data science, machine learning (ML), and artificial intelligence (AI) in general. In turn, these enhancements have brought about incredible innovation in deep reinforcement learning (DRL) that have allowed it to play games, previously thought to be impossible. DRL is now able to tackle game environments such as the classic Atari 2600 series and play them better than a human. In this chapter, we'll look at what new features in DL allow DRL to play visual state games, such as Atari games. First, we'll look at how a game screen can be used as a visual state. Then, we'll understand how DL can consume a visual state with a new component called convolutional neural networks (CNNs). After, we'll use that knowledge to...
Hands-On Reinforcement Learning for Games
By :
Hands-On Reinforcement Learning for Games
By:
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)
Preface
Section 1: Exploring the Environment
Free Chapter
Understanding Rewards-Based Learning
Dynamic Programming and the Bellman Equation
Monte Carlo Methods
Temporal Difference Learning
Exploring SARSA
Section 2: Exploiting the Knowledge
Going Deep with DQN
Going Deeper with DDQN
Policy Gradient Methods
Optimizing for Continuous Control
All about Rainbow DQN
Exploiting ML-Agents
DRL Frameworks
Section 3: Reward Yourself
3D Worlds
From DRL to AGI
Other Books You May Enjoy
Customer Reviews