{"title":"Parallel Distributed Implementation of Neuroevolution of Augmenting Topologies in Continuous Control Tasks","authors":"I. Achour, A. Doroshenko","doi":"10.1109/ATIT54053.2021.9678858","DOIUrl":null,"url":null,"abstract":"This paper proposes a novel distributed implementation of neuroevolution of augmenting topologies method, which, considering the availability of sufficient computational resources, allows drastically speed up the process of optimal neural network configuration search. The proposed solution includes batch genome evaluation for the purpose of performance optimization, fair, and even computational resources usage. The benchmarking shows that the generated neural networks evaluation process can give orders of magnitude increase of efficiency on the demonstrated continuous control task and computational environment.","PeriodicalId":368050,"journal":{"name":"2021 IEEE 3rd International Conference on Advanced Trends in Information Theory (ATIT)","volume":"115 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 IEEE 3rd International Conference on Advanced Trends in Information Theory (ATIT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ATIT54053.2021.9678858","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
This paper proposes a novel distributed implementation of neuroevolution of augmenting topologies method, which, considering the availability of sufficient computational resources, allows drastically speed up the process of optimal neural network configuration search. The proposed solution includes batch genome evaluation for the purpose of performance optimization, fair, and even computational resources usage. The benchmarking shows that the generated neural networks evaluation process can give orders of magnitude increase of efficiency on the demonstrated continuous control task and computational environment.