Book Image

Hands-On Deep Learning for Games

By : Micheal Lanham
Book Image

Hands-On Deep Learning for Games

By: Micheal Lanham

Overview of this book

The number of applications of deep learning and neural networks has multiplied in the last couple of years. Neural nets has enabled significant breakthroughs in everything from computer vision, voice generation, voice recognition and self-driving cars. Game development is also a key area where these techniques are being applied. This book will give an in depth view of the potential of deep learning and neural networks in game development. We will take a look at the foundations of multi-layer perceptron’s to using convolutional and recurrent networks. In applications from GANs that create music or textures to self-driving cars and chatbots. Then we introduce deep reinforcement learning through the multi-armed bandit problem and other OpenAI Gym environments. As we progress through the book we will gain insights about DRL techniques such as Motivated Reinforcement Learning with Curiosity and Curriculum Learning. We also take a closer look at deep reinforcement learning and in particular the Unity ML-Agents toolkit. By the end of the book, we will look at how to apply DRL and the ML-Agents toolkit to enhance, test and automate your games or simulations. Finally, we will cover your possible next steps and possible areas for future learning.
Table of Contents (18 chapters)
Free Chapter
1
Section 1: The Basics
6
Section 2: Deep Reinforcement Learning
14
Section 3: Building Games

Analyzing the testing process

One of the key features that ML-Agents is currently missing is extra training analytics (beyond what is provided by the console and TensorBoard). A key feature that could be crucial (and which is not difficult to add) is training analytics. This could be implemented with the Unity Analytics service that is free to try with all games. Since this isn't a current feature in ML-Agents, it is one that we will add in the next exercise, by adding our own training analytics system:

  1. Open the Unity editor, and from the menu, select Window | General | Services. This will open a new window called Services, usually over the top of the Inspector window.
  2. Click on the Analytics service in the newly opened Services window. You will need to progress through a couple of screens, asking for your preferences and acknowledgment, as shown in the following screenshot...