Book Image

Hands-On Neuroevolution with Python

By : Iaroslav Omelianenko
Book Image

Hands-On Neuroevolution with Python

By: Iaroslav Omelianenko

Overview of this book

Neuroevolution is a form of artificial intelligence learning that uses evolutionary algorithms to simplify the process of solving complex tasks in domains such as games, robotics, and the simulation of natural processes. This book will give you comprehensive insights into essential neuroevolution concepts and equip you with the skills you need to apply neuroevolution-based algorithms to solve practical, real-world problems. You'll start with learning the key neuroevolution concepts and methods by writing code with Python. You'll also get hands-on experience with popular Python libraries and cover examples of classical reinforcement learning, path planning for autonomous agents, and developing agents to autonomously play Atari games. Next, you'll learn to solve common and not-so-common challenges in natural computing using neuroevolution-based algorithms. Later, you'll understand how to apply neuroevolution strategies to existing neural network designs to improve training and inference performance. Finally, you'll gain clear insights into the topology of neural networks and how neuroevolution allows you to develop complex networks, starting with simple ones. By the end of this book, you will not only have explored existing neuroevolution-based algorithms, but also have the skills you need to apply them in your research and work assignments.
Table of Contents (18 chapters)
Free Chapter
1
Section 1: Fundamentals of Evolutionary Computation Algorithms and Neuroevolution Methods
4
Section 2: Applying Neuroevolution Methods to Solve Classic Computer Science Problems
9
Section 3: Advanced Neuroevolution Methods
14
Section 4: Discussion and Concluding Remarks

Visual discrimination experiment setup

In our experiment, during the training of the discriminator ANN, we use the resolution of the visual and target fields fixed at 11 x 11. Thus, the connective CPPN must learn the correct connectivity pattern between the 121 inputs of the visual field and the 121 outputs of the target fields, which results in a total of 14,641 potential connection weights.

The following diagram shows the scheme of the substrate for the discriminator ANN:

The state-space sandwich substrate of the discriminator ANN

The discriminator ANN shown in the diagram has two layers with nodes forming one two-dimensional planar grid per layer. The connective CPPN draws the connectivity patterns by connecting nodes from one layer to another.

At each generation of the evolution, each individual in the population (the genome encoding the CPPN) is evaluated for its ability...