Distributed implementation of neuroevolution of augmenting topologies method

• Дата: 2021
• Автори: Achour, I.Z., Doroshenko, A.Yu.
• Формат: Стаття
• Мова: Ukrainian
• Опубліковано: PROBLEMS IN PROGRAMMING 2021
• Теми: NEAT; neuroevolution of augmenting topologies; artificial neural networks; reinforcement learning; genetic algorithms; distributed computing; cloud computing; UDC 004.272.26 + 004.021 + 004.032.26
• Онлайн доступ: https://pp.isofts.kiev.ua/index.php/ojs1/article/view/467
• Назва журналу: Problems in programming

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