Published on Thu May 03 2018

VINE: An Open Source Interactive Data Visualization Tool for Neuroevolution

Rui Wang, Jeff Clune, Kenneth O. Stanley

VINE (Visual Inspector for NeuroEvolution) is an interactive data visualization tool. VINE works seamlessly with a breadth of neuroevolution algorithms, including evolution strategies and genetic algorithms.

0
0
0
Abstract

Recent advances in deep neuroevolution have demonstrated that evolutionary algorithms, such as evolution strategies (ES) and genetic algorithms (GA), can scale to train deep neural networks to solve difficult reinforcement learning (RL) problems. However, it remains a challenge to analyze and interpret the underlying process of neuroevolution in such high dimensions. To begin to address this challenge, this paper presents an interactive data visualization tool called VINE (Visual Inspector for NeuroEvolution) aimed at helping neuroevolution researchers and end-users better understand and explore this family of algorithms. VINE works seamlessly with a breadth of neuroevolution algorithms, including ES and GA, and addresses the difficulty of observing the underlying dynamics of the learning process through an interactive visualization of the evolving agent's behavior characterizations over generations. As neuroevolution scales to neural networks with millions or more connections, visualization tools like VINE that offer fresh insight into the underlying dynamics of evolution become increasingly valuable and important for inspiring new innovations and applications.

Fri Jul 11 2014
Neural Networks
A Proposed Infrastructure for Adding Online Interaction to Any Evolutionary Domain
Worldwide Infrastructure for Neuroevolution (WIN) is a collection of software packages built on top of Node.js. WIN Online is the public interface for WIN, providing an online collection of domains built with the WIN library.
0
0
0
Mon Dec 18 2017
Neural Networks
On the Relationship Between the OpenAI Evolution Strategy and Stochastic Gradient Descent
Stochastic gradient descent (SGD) has moved to the heart of leading approaches to reinforcement learning (RL) OpenAI showed that a particular kind of evolution strategy (ES) can rival the performance of SGD-based deep RL methods with large neural networks.
0
0
0
Mon Dec 24 2007
Neural Networks
GUIDE: Unifying Evolutionary Engines through a Graphical User Interface
GUIDE is a Graphical User Interface for DREAM Experiments. It unifies all kinds of EAs into a single panel, as far as evolution parameters are concerned. It is a fantastic pedagogic tool to teach EAs to students and newcomers to the field.
0
0
0
Tue Feb 12 2019
Neural Networks
Guiding Neuroevolution with Structural Objectives
The structure and performance of neural networks are intimately connected. Guiding such neuroevolution with additional objectives related to network structure has been shown to improve performance in some cases. We propose two new structural objectives and test their ability to guide evolving neural networks.
0
0
0
Mon Dec 18 2017
Neural Networks
Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning
Deep artificial neural networks (DNNs) are typically trained via gradient-based learning algorithms, namely backpropagation. We demonstrate that combining DNNs with novelty search, which encourages exploration on tasks with deceptive or sparse reward functions, can solve a high-dimensional problem.
1
0
0
Tue Feb 11 2020
Neural Networks
Neuroevolution of Neural Network Architectures Using CoDeepNEAT and Keras
Machine learning is a huge field of study in computer science and statistics. A large portion of the work involved in a machine learning project is to define the best type of algorithm to solve a given problem. The purpose of this work is to propose an adapted implementation of a well-established evolutionary technique.
0
0
0