Parallel Distributed Implementation of Neuroevolution of Augmenting Topologies in Continuous Control Tasks

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...

Full description

Saved in:
Bibliographic Details
Published in:2021 IEEE 3rd International Conference on Advanced Trends in Information Theory (ATIT) pp. 267 - 271
Main Authors: Achour, Illia, Doroshenko, Anatoliy
Format: Conference Proceeding
Language:English
Published: IEEE 15.12.2021
Subjects:
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
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.
AbstractList 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.
Author Achour, Illia
Doroshenko, Anatoliy
Author_xml – sequence: 1
  givenname: Illia
  surname: Achour
  fullname: Achour, Illia
  email: ilyaachour@gmail.com
  organization: National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute",Information Systems and Technologies Department,Kyiv,Ukraine
– sequence: 2
  givenname: Anatoliy
  surname: Doroshenko
  fullname: Doroshenko, Anatoliy
  email: doroshenkoanatoliy2@gmail.com
  organization: National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute",Information Systems and Technologies Department,Kyiv,Ukraine
BookMark eNo1j8tKxDAYhSPowhl9AkHyAq25N12WeisM6qKuh8z0b4mmTUkawbd3RsfVOXwcDnwrdD75CRC6pSSnlJR3Vdu0UhDJc0YYzUtVaC31GVpRpaTgWhTlJfp4M8E4Bw7f27gEu0sLdLgZZwcjTItZrJ-w7_ELpODhy7v0T6o0HBd2GnDrZ-_8YCFiO-HaH2nyKf7W4B1uTfyMV-iiNy7C9SnX6P3xoa2fs83rU1NXm8xSqpdMKyo6TgzlBHRhpIE9A-CFZoYStpfMKClBqZ6TYsco9GV30DUA0BEmBOdrdPP3aw9sOwc7mvC9PenzH1kwV5U
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/ATIT54053.2021.9678858
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE/IET Electronic Library (IEL) (UW System Shared)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 1665438479
9781665438476
EndPage 271
ExternalDocumentID 9678858
Genre orig-research
GroupedDBID 6IE
6IL
CBEJK
RIE
RIL
ID FETCH-LOGICAL-i118t-8614d30a130e87a5aec2ee3782a102c52a655e66f307b21ef9d110aeeed024433
IEDL.DBID RIE
IngestDate Thu Jun 29 18:37:55 EDT 2023
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i118t-8614d30a130e87a5aec2ee3782a102c52a655e66f307b21ef9d110aeeed024433
PageCount 5
ParticipantIDs ieee_primary_9678858
PublicationCentury 2000
PublicationDate 2021-Dec.-15
PublicationDateYYYYMMDD 2021-12-15
PublicationDate_xml – month: 12
  year: 2021
  text: 2021-Dec.-15
  day: 15
PublicationDecade 2020
PublicationTitle 2021 IEEE 3rd International Conference on Advanced Trends in Information Theory (ATIT)
PublicationTitleAbbrev ATIT
PublicationYear 2021
Publisher IEEE
Publisher_xml – name: IEEE
Score 1.7791502
Snippet This paper proposes a novel distributed implementation of neuroevolution of augmenting topologies method, which, considering the availability of sufficient...
SourceID ieee
SourceType Publisher
StartPage 267
SubjectTerms artificial neural networks
Benchmark testing
cloud computing
Computational efficiency
genetic algorithms
Genomics
NEAT
Network topology
Neural networks
neuroevolution of augmenting topologies
parallel distributed computing
Process control
reinforcement learning
Topology
Title Parallel Distributed Implementation of Neuroevolution of Augmenting Topologies in Continuous Control Tasks
URI https://ieeexplore.ieee.org/document/9678858
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV09T8MwELXaioEJUIv4lgdG0jbOh-2xAipYqg5B6lY5zrkKFAelTX8_ZzcqQmJhs6xIkc9J3j3n3j1C7kWOmJVGEEjOTBArFQaYVUMQMVBKMYMQqb3ZBJ_NxGIh5x3ycNDCAIAvPoOhG_p_-UWlG3dUNpL4ZRWJ6JIu53yv1WpFv-FYjibZa-byjwhZHwuH7cW_XFM8aExP_ne7UzL4Ud_R-QFXzkgHbJ-8z1XtbE_W9Mm1unUuVVBQ39v3s5UPWVoZ6pttwK59oNzMpFn5kiC7otneEQHJMS0tdY2pStsg9ffDulrTTG0-NgPyNn3OHl-C1ichKJEebAOBEFtEY4VwBIKrRIFmABFiv8L0QSdMpUkCaWrwfc5ZCEYWGDCF6y0QoeMoOic9W1m4IDQ3Js-RkUlhWFxoI7RkOoyViE3MwYwvSd_Fafm1b4WxbEN09ff0NTl2W-GqP8LkhvS2dQO35EjvtuWmvvP79w06GKEW
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PT8IwFG4QTfSkBoy_7cGjA9Z1W3ckKoGIhMNMuJGueyVT3Mxg_P2-lgVj4sVb0yxZ-rrte1_3vvcRci8SxKzAAycKmXa4lK6DWTU4HgMpJdMIkcqaTYSTiZjNommDPOy0MABgi8-gY4b2X35aqMoclXUj_LIKX-yRfZ9z5m7VWrXs1-1F3X48ik0G4iHvY26nvvyXb4qFjcHx_254Qto_-js63SHLKWlA3iLvU1ka45MlfTLNbo1PFaTUdvf9rAVEOS00te02YFM_UmamXy1sUVC-oPHWEwHpMc1yalpTZXmF5N8Oy2JJY7n6WLXJ2-A5fhw6tVOCkyFBWDsCQTb1ehIBCUQofQmKAXiI_hITCOUzGfg-BIHGNzphLugoxYBJXG-KGM0974w08yKHc0ITrZMEOVkkNOOp0kJFTLlcCq55CLp3QVomTvOvbTOMeR2iy7-n78jhMH4dz8ejycsVOTLbYmpBXP-aNNdlBTfkQG3W2aq8tXv5DcTKpF0
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2021+IEEE+3rd+International+Conference+on+Advanced+Trends+in+Information+Theory+%28ATIT%29&rft.atitle=Parallel+Distributed+Implementation+of+Neuroevolution+of+Augmenting+Topologies+in+Continuous+Control+Tasks&rft.au=Achour%2C+Illia&rft.au=Doroshenko%2C+Anatoliy&rft.date=2021-12-15&rft.pub=IEEE&rft.spage=267&rft.epage=271&rft_id=info:doi/10.1109%2FATIT54053.2021.9678858&rft.externalDocID=9678858