{"id":"https://openalex.org/W4318603319","doi":"https://doi.org/10.1109/ssci51031.2022.10022160","title":"Reinforcement Learning for Solving Communication Problems in Shepherding","display_name":"Reinforcement Learning for Solving Communication Problems in Shepherding","publication_year":2022,"publication_date":"2022-12-04","ids":{"openalex":"https://openalex.org/W4318603319","doi":"https://doi.org/10.1109/ssci51031.2022.10022160"},"language":"en","primary_location":{"id":"doi:10.1109/ssci51031.2022.10022160","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ssci51031.2022.10022160","pdf_url":null,"source":{"id":"https://openalex.org/S4363605327","display_name":"2022 IEEE Symposium Series on Computational Intelligence (SSCI)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Symposium Series on Computational Intelligence (SSCI)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062388478","display_name":"Reem E. Mohamed","orcid":"https://orcid.org/0000-0002-6992-6608"},"institutions":[{"id":"https://openalex.org/I159247623","display_name":"Mansoura University","ror":"https://ror.org/01k8vtd75","country_code":"EG","type":"education","lineage":["https://openalex.org/I159247623"]},{"id":"https://openalex.org/I188329596","display_name":"University of Canberra","ror":"https://ror.org/04s1nv328","country_code":"AU","type":"education","lineage":["https://openalex.org/I188329596"]},{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU","EG"],"is_corresponding":false,"raw_author_name":"Reem E. Mohamed","raw_affiliation_strings":["School of Engineering and Information Technology, University of New South Wales,Canberra ACT,Australia","Electronics and Communications Engineering Department, Faculty of Engineering, Mansoura University, Egypt","School of Engineering and Information Technology, University of New South Wales, Canberra ACT, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Engineering and Information Technology, University of New South Wales,Canberra ACT,Australia","institution_ids":["https://openalex.org/I188329596","https://openalex.org/I31746571"]},{"raw_affiliation_string":"Electronics and Communications Engineering Department, Faculty of Engineering, Mansoura University, Egypt","institution_ids":["https://openalex.org/I159247623"]},{"raw_affiliation_string":"School of Engineering and Information Technology, University of New South Wales, Canberra ACT, Australia","institution_ids":["https://openalex.org/I188329596","https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063874940","display_name":"Saber Elsayed","orcid":"https://orcid.org/0000-0003-0836-6122"},"institutions":[{"id":"https://openalex.org/I188329596","display_name":"University of Canberra","ror":"https://ror.org/04s1nv328","country_code":"AU","type":"education","lineage":["https://openalex.org/I188329596"]},{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Saber Elsayed","raw_affiliation_strings":["School of Engineering and Information Technology, University of New South Wales,Canberra ACT,Australia","School of Engineering and Information Technology, University of New South Wales, Canberra ACT, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Engineering and Information Technology, University of New South Wales,Canberra ACT,Australia","institution_ids":["https://openalex.org/I188329596","https://openalex.org/I31746571"]},{"raw_affiliation_string":"School of Engineering and Information Technology, University of New South Wales, Canberra ACT, Australia","institution_ids":["https://openalex.org/I188329596","https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068978340","display_name":"Robert Hunjet","orcid":"https://orcid.org/0000-0001-7345-6082"},"institutions":[{"id":"https://openalex.org/I1303474014","display_name":"Defence Science and Technology Group","ror":"https://ror.org/05ddrvt52","country_code":"AU","type":"government","lineage":["https://openalex.org/I1303474014","https://openalex.org/I2801453606","https://openalex.org/I3139952251"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Robert Hunjet","raw_affiliation_strings":["Defence Science and Technology Group,Edinburgh,SA,Australia","Defence Science and Technology Group, Edinburgh, SA, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Defence Science and Technology Group,Edinburgh,SA,Australia","institution_ids":["https://openalex.org/I1303474014"]},{"raw_affiliation_string":"Defence Science and Technology Group, Edinburgh, SA, Australia","institution_ids":["https://openalex.org/I1303474014"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022974795","display_name":"Hussein A. Abbass","orcid":"https://orcid.org/0000-0002-8837-0748"},"institutions":[{"id":"https://openalex.org/I188329596","display_name":"University of Canberra","ror":"https://ror.org/04s1nv328","country_code":"AU","type":"education","lineage":["https://openalex.org/I188329596"]},{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hussein Abbass","raw_affiliation_strings":["School of Engineering and Information Technology, University of New South Wales,Canberra ACT,Australia","School of Engineering and Information Technology, University of New South Wales, Canberra ACT, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Engineering and Information Technology, University of New South Wales,Canberra ACT,Australia","institution_ids":["https://openalex.org/I188329596","https://openalex.org/I31746571"]},{"raw_affiliation_string":"School of Engineering and Information Technology, University of New South Wales, Canberra ACT, Australia","institution_ids":["https://openalex.org/I188329596","https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19694305,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"130","issue":null,"first_page":"1626","last_page":"1635"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7324858903884888},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.630571186542511},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5970722436904907},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.5852941870689392},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5594910383224487},{"id":"https://openalex.org/keywords/transmitter","display_name":"Transmitter","score":0.5553508996963501},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5423629283905029},{"id":"https://openalex.org/keywords/swarm-behaviour","display_name":"Swarm behaviour","score":0.4560913145542145},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.455729603767395},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4318516254425049},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4272994101047516},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.37836602330207825},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31661251187324524},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.27160608768463135},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2364790439605713},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12592914700508118},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11597970128059387},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0991450846195221}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7324858903884888},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.630571186542511},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5970722436904907},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.5852941870689392},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5594910383224487},{"id":"https://openalex.org/C47798520","wikidata":"https://www.wikidata.org/wiki/Q190157","display_name":"Transmitter","level":3,"score":0.5553508996963501},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5423629283905029},{"id":"https://openalex.org/C181335050","wikidata":"https://www.wikidata.org/wiki/Q14915018","display_name":"Swarm behaviour","level":2,"score":0.4560913145542145},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.455729603767395},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4318516254425049},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4272994101047516},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.37836602330207825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31661251187324524},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.27160608768463135},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2364790439605713},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12592914700508118},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11597970128059387},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0991450846195221},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ssci51031.2022.10022160","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ssci51031.2022.10022160","pdf_url":null,"source":{"id":"https://openalex.org/S4363605327","display_name":"2022 IEEE Symposium Series on Computational Intelligence (SSCI)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Symposium Series on Computational Intelligence (SSCI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5489323064","display_name":null,"funder_award_id":"N62909-18-1-2140","funder_id":"https://openalex.org/F4320338298","funder_display_name":"Office of Naval Research Global"}],"funders":[{"id":"https://openalex.org/F4320338298","display_name":"Office of Naval Research Global","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1988737313","https://openalex.org/W2067040941","https://openalex.org/W2121863487","https://openalex.org/W2123969847","https://openalex.org/W2153353843","https://openalex.org/W2170591991","https://openalex.org/W2502094132","https://openalex.org/W2563698505","https://openalex.org/W2783042660","https://openalex.org/W2845027230","https://openalex.org/W2905808321","https://openalex.org/W2964339789","https://openalex.org/W3003784105","https://openalex.org/W3106122926","https://openalex.org/W3119359686","https://openalex.org/W3152209007","https://openalex.org/W3190532145","https://openalex.org/W4200486140","https://openalex.org/W4206761079","https://openalex.org/W4206822501","https://openalex.org/W4367721796"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W1985560493","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3168977894","https://openalex.org/W187740018"],"abstract_inverted_index":{"Swarm":[0],"guidance":[1],"is":[2,47,206],"one":[3],"of":[4,8,42,56,110,114,211],"the":[5,13,17,21,25,38,43,54,60,71,82,89,95,99,108,112,115,120,123,127,168,186,191,200,209],"modern":[6],"applications":[7],"autonomous":[9],"systems.":[10],"In":[11,103],"it,":[12],"controller":[14],"acts":[15,23,131],"as":[16,24,132],"transmitter":[18],"(Tx),":[19],"and":[20,73,80,84],"actuator":[22],"receiver":[26],"(Rx),":[27],"exchanging":[28],"control":[29,50],"commands":[30,124],"through":[31,59,67,173],"a":[32,48,133,137,141],"wireless":[33,61],"communication":[34,62,90,202],"channel":[35,63,91],"to":[36,70,77,88,118,126,153,166,197],"complete":[37],"task.":[39],"The":[40,178],"success":[41,55,97,193],"shepherding":[44,138],"task,":[45],"which":[46,205],"swarm":[49],"application,":[51],"depends":[52],"on":[53],"these":[57],"transmissions":[58],"that":[64,130,181],"may":[65],"vary":[66],"time":[68,79],"due":[69],"Tx's":[72],"Rx's":[74],"mobility.":[75],"Therefore,":[76],"save":[78],"energy,":[81],"Tx":[83,116],"Rx":[85,128],"must":[86],"adapt":[87],"changes":[92],"while":[93],"ensuring":[94],"task's":[96,192],"in":[98,122,136,157],"shortest":[100],"possible":[101],"time.":[102],"this":[104],"paper,":[105],"we":[106,147],"model":[107],"problem":[109],"optimising":[111],"mobility":[113,172],"(controller)":[117],"overcome":[119],"noise":[121],"sent":[125],"(actuator)":[129],"robotic":[134],"sheepdog":[135],"scenario":[139],"with":[140,185],"Markov":[142],"decision":[143],"process":[144],"(MDP).":[145],"Then,":[146],"propose":[148],"an":[149],"incremental":[150,187],"search":[151,188],"method":[152,189],"find":[154],"near-optimal":[155],"actions":[156],"real-time.":[158],"Furthermore,":[159],"two":[160],"different":[161],"reward":[162],"functions":[163],"are":[164],"used":[165],"help":[167],"CU":[169],"improve":[170],"its":[171],"online":[174],"learning":[175],"using":[176,182],"Q-learning.":[177],"results":[179],"proved":[180],"Q-learning":[183],"combined":[184],"improved":[190],"rate":[194],"($SR$)":[195],"sometimes":[196],"exceed":[198],"the$SR$in":[199],"ideal":[201],"link":[203],"scenario,":[204],"double":[207],"its$SR$in":[208],"presence":[210],"noise.":[212]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}