SharpNEAT

NEAT is NeuroEvolution of Augmenting Topologies, an evolutionary algorithm devised by Kenneth Stanley of the University of Central Florida School of Electrical Engineering and Computer Science.

SharpNEAT is a complete implementation of NEAT written in C# and targeting the .Net runtime environment (running on both MS Windows and Mono/Linux).

Research using SharpNEAT

Note. The HyperNEAT papers linked below use HyperSharpNEAT, a version of SharpNEAT extended by David B. D'Ambrosio at the University of Central Florida to implement 'HyperNEAT' - an extension to the NEAT method that uses a new form of indirect/generative encoding.

Many of the links below point to papers published by the EPLEX research group, to see all EPLEX publications including papers not using SharpNeat or HyperSharpNeat and also the very latest papers, please visit EPLEX Publications.

2012

Multirobot Behavior Synchronization through Direct Neural Network Communication
David B. D'Ambrosio, Skyler Goodell, Joel Lehman, Sebastian Risi, and Kenneth O. Stanley (2012).
In: Proceedings of the 5th International Conference on Intelligent Robotics and Applications (ICIRA-2012). New York, NY: Springer-Verlang, 2012.
An Enhanced Hypercube-Based Encoding for Evolving the Placement, Density and Connectivity of Neurons
Sebastian Risi and Kenneth O. Stanley (2012).
To appear in: Artificial Life journal. Cambridge, MA: MIT Press, 2012
A Unified Approach to Evolving Plasticity and Neural Geometry
Sebastian Risi and Kenneth O. Stanley (2012).
In: Proceedings of the International Joint Conference on Neural Networks (IJCNN 2012). Piscataway, NJ: IEEE, 2012 (8 pages).
Winner of the Best Student Paper Award at IJCNN-2012
Rewarding Reactivity to Evolve Robust Controllers without Multiple Trials or Noise
Joel Lehman, Sebastian Risi, David B. D'Ambrosio, and Kenneth O. Stanley (2012).
To appear in: Proceedings of the Thirteenth International Conference on Artificial Life (ALIFE XIII). Cambridge, MA: MIT Press, 2012 (8 pages).

2011

Task Switching in Multirobot Learning through Indirect Encoding
David B. D'Ambrosio, Joel Lehman, Sebastian Risi, and Kenneth O. Stanley (2011).
In: Proceedings of the International Conference on Intelligent Robots and Systems (IROS 2011 San Fransisco, CA)

2010

Indirectly Encoding Neural Plasticity as a Pattern of Local Rules
Sebastian Risi and Kenneth O. Stanley (2010).
To appear in: Proceedings of the 11th International Conference on Simulation of Adaptive Behavior (SAB 2010). New York, NY: Springer (11 pages)
Evolving the Placement and Density of Neurons in the HyperNEAT Substrate
Sebastian Risi, Joel Lehman, and Kenneth O. Stanley (2010).
To appear in: Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2010). New York, NY:ACM (8 pages)
Evolving Policy Geometry for Scalable Multiagent Learning
David B. D'Ambrosio, Joel Lehman, Sebastian Risi, and Kenneth O. Stanley (2010).
In: Proceedings of the Ninth International Conference on Autonomous Agents and Multiagent Systems (AAMAS-2010). (8 pages)
Note:
This paper is accompanied with a set of videos at http://eplex.cs.ucf.edu/mahnaamas2010.html

2009

Using Neural Networks for Strategy Selection in Real-Time Strategy Games
Thomas Randall, Peter Cowling, Roderick Baker and Ping Jiang (2009).
School of Computing, Informatics and Media, Univ. of Bradford.
A Hypercube-Based Indirect Encoding for Evolving Large-Scale Neural Networks
Kenneth O. Stanley, David B. D'Ambrosio, and Jason Gauci (2009).
To appear in: Artificial Life journal. Cambridge, MA: MIT Press, 2009 (Manuscript 39 pages)
HyperNEAT Controlled Robots Learn How to Drive on Roads in Simulated Environment
Jan Drchal, Jan Koutník, Miroslav Snorek (2009).
Computational Intelligence Group, Department of Computer Science and Engineering, Faculty of Electrical Engineering, Czech Technical University, Prague

2008

Generative Encoding for Multiagent Learning
David B. D'Ambrosio and Kenneth O. Stanley
In: Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2008). New York, NY: ACM, 2008 (8 pages)
Winner of the Best Paper Award in Generative and Developmental Systems at GECCO-2008
Can Opponent Models Aid Poker Player Evolution?
R.J.S.Baker, Member, IEEE, P.I.Cowling, Member, IEEE, T.W.G.Randall, Member, IEEE, and P.Jiang, Member, IEEE.
Interactively Evolved Modular Neural Networks for Game Agent Control
John Reeder, Roberto Miguez, Jessica Sparks, Michael Georgiopoulos, and Georgios Anagnostopoulos.

2007

A Novel Generative Encoding for Exploiting Neural Network Sensor and Output Geometry
David B. D'Ambrosio and Kenneth O. Stanley
Nominated for Best Paper Award in Generative and Developmental Systems, GECCO 2007

David D'Ambrosio and Kenneth Stanley at the University of Central Florida used their extended version of SharpNEAT - HyperSharpNEAT - in this paper presented at GECCO 2007. This was one of two papers introducing HyperNEAT, a powerful new indirect encoding.

Their HyperSharpNEAT releases are available from the UCF EPLEX software download page.
Evolving Explicit Opponent Models in Game Playing
Alan J. Lockett, Charles L. Chen, and Risto Miikkulainen, The University of Texas at Austin.
Wesley Tansey extended SharpNEAT to allow parallel processing across multiple CPUs while at Virginia Tech. This work is hosted on Codeplex as ParaSharpNEAT.

2006

Exploiting Regularity Without Development
Kenneth O. Stanley, School of Electrical Engineering and Computer Science, The University of Central Florida

SharpNEAT on the web

Genetic Art with SharpNEAT. Holger Ferstl created this SharpNEAT based application that evolves images by allowing a user to iteratively select their favourite from a page of candidate images. The application was built on the .Net 2.0 framework and is capable of generating some really nice output. Many thanks to Holger. Now for the eye candy - these were generated by me, there are more examples through the link...

Experiment/Investigation write ups