Distributed implementation of neuroevolution of augmenting topologies method

I.Z. Achour, A.Yu. Doroshenko


Despite the neuroevolution of augmenting topologies method strengths, like the capability to be used in cases where the formula for a cost function and the topology of the neural network are difficult to determine, one of the main problems of such methods is slow convergence towards optimal results, especially in cases with complex and challenging environments. This paper proposes the novel distributed implementation of neuroevolution of augmenting topologies method, which considering availability of sufficient computational resources allows drastically speed up the process of optimal neural network configuration search. Batch genome evaluation was implemented for the means of proposed solution performance optimization, fair, and even computational resources usage. The proposed distributed implementation benchmarking shows that the generated neural networks evaluation process gives a manifold increase of efficiency on the demonstrated task and computational environment.

Prombles in programming 2021; 3: 03-15



NEAT; neuroevolution of augmenting topologies; artificial neural networks; reinforcement learning; genetic algorithms; distributed computing; cloud computing

Full Text:

PDF (Ukrainian)


Evolution 101: Neuroevolution | BEACON. BEACON | An NSF Center for the Study of Evolution in Action. URL: https:// tion-101-neuroevolution/ (date of access: 08.08.2021).

Subbotin S., Oliinyk A., Oliinyk O. Noniterative, Evolutionary, and Multiagent Methods of Synthesis of Fuzzy Logic and Neural Network Models / ed. by S. O. Subbotin. Zaporizhzhya : ZNTU, 2009. 375 p.

Stanley K. O. Efficient evolution of neural networks through complexification : Thesis. 2004. URL: (date of access: 08.08.2021).

NeuroEvolution of Augmenting Topologies. Department of Computer Science, College of Engineering and Computer Science@UCF. URL: neat.html (date of access: 08.08.2021).

Stanley K. O., Miikkulainen R. Evolving Neural Networks through Augmenting Topologies. Evolutionary Computation. 2002. Vol. 10, no. 2. P. 99-127. (date of access: 08.08.2021).

Stanley K. O., Bryant B. D., Miikkulainen R. Real-Time Neuroevolution in the NERO Video Game. IEEE Transactions on Evolutionary Computation. 2005. Vol. 9, no. 6. P. 653-668. (date of access: 08.08.2021).

Stanley K. O., Miikkulainen R. Competitive Coevolution through Evolutionary Complexification. Journal of Artificial Intelligence Research. 2004. Vol. 21. P. 63-100. URL: (date of access: 08.08.2021).

Green C. SharpNEAT Neuroevolution Framework. SharpNEAT Neuroevolution Framework. URL: (date of access: 08.08.2021).

Andrews G. R. Foundations of multithreaded, parallel, and distributed programming. Reading, Mass : Addison-Wesley, 2000. 664 p.

Arora S. Computational complexity: A modern approach. Cambridge : Cambridge University Press, 2009.

Lynch N. A. Distributed algorithms. San Francisco, Calif : Morgan Kaufmann, 1997. 872 p.

Peleg D. Distributed computing: A locality-sensitive approach. Philadelphia : Society for Industrial and Applied Mathematics, 2000.

Booch G., Rumbaugh J., Jacobson I. Unified Modeling Language User Guide, The (2nd Edition) (The Addison-Wesley Object Technology Series). 2nd ed. Addison-Wes- ley Professional, 2005. 496 p.

ASP.NET documentation. Developer tools, technical documentation and cod- ing examples | Microsoft Docs. URL: core/?view=aspnetcore-5.0 (date of access: 08.08.2021).

Introduction to gRPC. gRPC. URL: https:// (date of access: 08.08.2021).

Language Guide | Protocol Buffers | Google Developers. Google Developers. URL: (date of access: 08.08.2021).

The 11-multiplexer Problem. GEP: Home. URL: CS2001/Section6/SS5/SSS2.htm (date of access: 08.08.2021).

Powering .NET 5 with AWS Graviton2: Benchmarks | Amazon Web Services. Amazon Web Services. URL: https://aws.ama- 5-with-aws-graviton2-benchmark-results/ (date of access: 08.08.2021).



  • There are currently no refbacks.