Skip to search formSkip to main contentSkip to account menu

Evolving Neural Networks through Augmenting Topologies

A method is presented, NeuroEvolution of Augmenting Topologies (NEAT), which outperforms the best fixed-topology method on a challenging benchmark reinforcement learning task and shows how it is possible for evolution to both optimize and complexify solutions simultaneously.
View on MIT Press (opens in a new tab)

Abandoning Objectives: Evolution Through the Search for Novelty Alone

In the maze navigation and biped walking tasks in this paper, novelty search significantly outperforms objective-based search, suggesting the strange conclusion that some problems are best solved by methods that ignore the objective.
View on MIT Press (opens in a new tab)

Compositional pattern producing networks: A novel abstraction of development

Results produced with CPPNs through interactive evolution of two-dimensional images show that such an encoding can nevertheless produce structural motifs often attributed to more conventional developmental abstractions, suggesting that local interaction may not be essential to the desirable properties of natural encoding in the way that is usually assumed.
View on Springer (opens in a new tab)

Exploiting Open-Endedness to Solve Problems Through the Search for Novelty

Decoupling the idea of open-ended search from only artificial life worlds, the raw search for novelty can be applied to real world problems and significantly outperforms objective-based search in the deceptive maze navigation task.
View Paper (opens in a new tab)

A Hypercube-Based Encoding for Evolving Large-Scale Neural Networks

The main conclusion is that the ability to explore the space of regular connectivity patterns opens up a new class of complex high-dimensional tasks to neuroevolution.
View on MIT Press (opens in a new tab)

Evolving a diversity of virtual creatures through novelty search and local competition

The results in an experiment evolving locomoting virtual creatures show that novelty search with local competition discovers more functional morphological diversity within a single run than models with global competition, which are more predisposed to converge.
View on ACM (opens in a new tab)

Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning

It is shown that combining DNNs with novelty search, which was designed to encourage exploration on tasks with deceptive or sparse reward functions, can solve a high-dimensional problem on which reward-maximizing algorithms fail, and expands the sense of the scale at which GAs can operate.
View PDF on arXiv (opens in a new tab)

Search-Based Procedural Content Generation: A Taxonomy and Survey

This article contains a survey of all published papers known to the authors in which game content is generated through search or optimisation, and ends with an overview of important open research problems.
View on IEEE (opens in a new tab)

Quality Diversity: A New Frontier for Evolutionary Computation

A new approach is investigated that hybridizes multiple views of behaviors (called behavior characterizations) in the same run, which succeeds in overcoming some of the challenges associated with searching for QD with respect to a behavior characterization that is not necessarily sufficient for generating both quality and diversity at the same time.
View via Publisher (opens in a new tab)

Efficient evolution of neural networks through complexification

This dissertation presents the NeuroEvolution of Augmenting Topologies (NEAT) method, which makes search for complex solutions feasible and is first shown faster than traditional approaches on a challenging reinforcement learning benchmark task, and used to successfully discover complex behavior in three challenging domains.
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)