{"id":"https://openalex.org/W2937399482","doi":"https://doi.org/10.3390/make1020035","title":"A Novel Heterogeneous Swarm Reinforcement Learning Method for Sequential Decision Making Problems","display_name":"A Novel Heterogeneous Swarm Reinforcement Learning Method for Sequential Decision Making Problems","publication_year":2019,"publication_date":"2019-04-16","ids":{"openalex":"https://openalex.org/W2937399482","doi":"https://doi.org/10.3390/make1020035","mag":"2937399482"},"language":"en","primary_location":{"id":"doi:10.3390/make1020035","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make1020035","pdf_url":"https://www.mdpi.com/2504-4990/1/2/35/pdf?version=1555421954","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2504-4990/1/2/35/pdf?version=1555421954","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014112728","display_name":"Zohreh Akbari","orcid":"https://orcid.org/0000-0001-8322-2722"},"institutions":[{"id":"https://openalex.org/I62318514","display_name":"University of Duisburg-Essen","ror":"https://ror.org/04mz5ra38","country_code":"DE","type":"education","lineage":["https://openalex.org/I62318514"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Zohreh Akbari","raw_affiliation_strings":["Institute for Computer Science and Business Information Systems (ICB), University of Duisburg-Essen, 45141 Essen, Germany"],"raw_orcid":"https://orcid.org/0000-0001-8322-2722","affiliations":[{"raw_affiliation_string":"Institute for Computer Science and Business Information Systems (ICB), University of Duisburg-Essen, 45141 Essen, Germany","institution_ids":["https://openalex.org/I62318514"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086033373","display_name":"Rainer Unland","orcid":null},"institutions":[{"id":"https://openalex.org/I12379730","display_name":"Pozna\u0144 University of Economics and Business","ror":"https://ror.org/0532c1x92","country_code":"PL","type":"education","lineage":["https://openalex.org/I12379730"]},{"id":"https://openalex.org/I62318514","display_name":"University of Duisburg-Essen","ror":"https://ror.org/04mz5ra38","country_code":"DE","type":"education","lineage":["https://openalex.org/I62318514"]}],"countries":["DE","PL"],"is_corresponding":false,"raw_author_name":"Rainer Unland","raw_affiliation_strings":["Department of Information Systems, Poznan University of Economics and Business, 61-875 Poznan, Poland","Institute for Computer Science and Business Information Systems (ICB), University of Duisburg-Essen, 45141 Essen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Systems, Poznan University of Economics and Business, 61-875 Poznan, Poland","institution_ids":["https://openalex.org/I12379730"]},{"raw_affiliation_string":"Institute for Computer Science and Business Information Systems (ICB), University of Duisburg-Essen, 45141 Essen, Germany","institution_ids":["https://openalex.org/I62318514"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5014112728"],"corresponding_institution_ids":["https://openalex.org/I62318514"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":1.5166,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.85243481,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"1","issue":"2","first_page":"590","last_page":"610"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10328","display_name":"Supply Chain and Inventory Management","score":0.9914000034332275,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10328","display_name":"Supply Chain and Inventory Management","score":0.9914000034332275,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9851999878883362,"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/T11182","display_name":"Auction Theory and Applications","score":0.9692000150680542,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/swarm-behaviour","display_name":"Swarm behaviour","score":0.8473686575889587},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7149600982666016},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6487343311309814},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6125600337982178},{"id":"https://openalex.org/keywords/homogeneous","display_name":"Homogeneous","score":0.5561429858207703},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5124788284301758},{"id":"https://openalex.org/keywords/decision-problem","display_name":"Decision problem","score":0.4699808657169342},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41208162903785706},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3215969204902649},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.31786489486694336},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14749902486801147},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13010674715042114}],"concepts":[{"id":"https://openalex.org/C181335050","wikidata":"https://www.wikidata.org/wiki/Q14915018","display_name":"Swarm behaviour","level":2,"score":0.8473686575889587},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7149600982666016},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6487343311309814},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6125600337982178},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.5561429858207703},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5124788284301758},{"id":"https://openalex.org/C115988155","wikidata":"https://www.wikidata.org/wiki/Q3262192","display_name":"Decision problem","level":2,"score":0.4699808657169342},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41208162903785706},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3215969204902649},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.31786489486694336},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14749902486801147},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13010674715042114},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3390/make1020035","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make1020035","pdf_url":"https://www.mdpi.com/2504-4990/1/2/35/pdf?version=1555421954","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.3390/make1020035","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make1020035","pdf_url":"https://www.mdpi.com/2504-4990/1/2/35/pdf?version=1555421954","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2937399482.pdf","grobid_xml":"https://content.openalex.org/works/W2937399482.grobid-xml"},"referenced_works_count":59,"referenced_works":["https://openalex.org/W84428182","https://openalex.org/W194148199","https://openalex.org/W206679605","https://openalex.org/W968045710","https://openalex.org/W1491322982","https://openalex.org/W1512942673","https://openalex.org/W1515891729","https://openalex.org/W1518858799","https://openalex.org/W1527187180","https://openalex.org/W1549353711","https://openalex.org/W1560973405","https://openalex.org/W1587442892","https://openalex.org/W1673310716","https://openalex.org/W1709679583","https://openalex.org/W1731081199","https://openalex.org/W1980237140","https://openalex.org/W1996542214","https://openalex.org/W2083533909","https://openalex.org/W2087778535","https://openalex.org/W2091565802","https://openalex.org/W2102660061","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2123457819","https://openalex.org/W2139229092","https://openalex.org/W2150884987","https://openalex.org/W2152445738","https://openalex.org/W2165131254","https://openalex.org/W2170596197","https://openalex.org/W2187726011","https://openalex.org/W2209334783","https://openalex.org/W2334782222","https://openalex.org/W2515000634","https://openalex.org/W2520735695","https://openalex.org/W2567566400","https://openalex.org/W2592052530","https://openalex.org/W2610550445","https://openalex.org/W2739343038","https://openalex.org/W2809330999","https://openalex.org/W3011120880","https://openalex.org/W3041202696","https://openalex.org/W3103262232","https://openalex.org/W3126694097","https://openalex.org/W3139377883","https://openalex.org/W4214717370","https://openalex.org/W4233757421","https://openalex.org/W4298114828","https://openalex.org/W6603424559","https://openalex.org/W6629566668","https://openalex.org/W6630897036","https://openalex.org/W6631000544","https://openalex.org/W6631445940","https://openalex.org/W6632181952","https://openalex.org/W6656844882","https://openalex.org/W6680875816","https://openalex.org/W6718806377","https://openalex.org/W6731453323","https://openalex.org/W6775686901","https://openalex.org/W6821409176"],"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":{"Sequential":[0],"Decision":[1,11,35],"Making":[2],"Problems":[3],"(SDMPs)":[4],"that":[5,18,50,76,106,175,233],"can":[6,13],"be":[7,14,42],"modeled":[8],"as":[9,71,126,195],"Markov":[10],"Processes":[12],"solved":[15],"using":[16],"methods":[17],"combine":[19],"Dynamic":[20],"Programming":[21],"(DP)":[22],"and":[23,32,58,121,186],"Reinforcement":[24],"Learning":[25],"(RL).":[26],"Depending":[27],"on":[28,93,118],"the":[29,33,104,112,154,165,204,211,238],"problem":[30,156],"scenarios":[31],"available":[34,94],"Makers":[36],"(DMs),":[37],"such":[38],"RL":[39,96,230],"algorithms":[40],"may":[41],"designed":[43,181],"for":[44],"single-agent":[45],"systems":[46,49,124],"or":[47,69,136,157],"multi-agent":[48],"either":[51],"consist":[52],"of":[53,74,103,111,139,153,167,191,213],"agents":[54,75,214],"with":[55,149],"individual":[56],"goals":[57],"decision":[59],"making":[60],"capabilities,":[61,147],"which":[62,142,178,209],"are":[63,179],"influenced":[64],"by":[65],"other":[66],"agent\u2019s":[67],"decisions,":[68],"behave":[70,194],"a":[72,79,100,150,172,196,220,227],"swarm":[73,95,197],"collaboratively":[77],"learn":[78],"single":[80],"objective.":[81],"Many":[82],"studies":[83,113],"have":[84,188],"been":[85],"conducted":[86],"in":[87,114,161,225],"this":[88,115],"area;":[89],"however,":[90],"when":[91,198],"concentrating":[92],"algorithms,":[97],"one":[98],"obtains":[99],"clear":[101],"view":[102],"areas":[105],"still":[107],"require":[108],"attention.":[109],"Most":[110],"area":[116],"focus":[117],"homogeneous":[119,140],"swarms":[120],"so":[122],"far,":[123],"introduced":[125],"Heterogeneous":[127,228],"Swarms":[128],"(HetSs)":[129],"merely":[130],"include":[131],"very":[132],"few,":[133],"i.e.,":[134],"two":[135,207],"three":[137],"sub-swarms":[138],"agents,":[141,177,208],"either,":[143],"according":[144],"to":[145,163,182,193,215,236],"their":[146],"deal":[148],"specific":[151,221],"sub-problem":[152],"general":[155],"exhibit":[158],"different":[159,184],"behaviors":[160],"order":[162],"reduce":[164],"risk":[166],"bias.":[168],"This":[169],"study":[170],"introduces":[171],"novel":[173],"approach":[174],"allows":[176,234],"originally":[180],"solve":[183,237],"problems":[185],"hence":[187],"higher":[189],"degrees":[190],"heterogeneity,":[192],"addressing":[199],"identical":[200],"sub-problems.":[201],"In":[202],"fact,":[203],"affinity":[205],"between":[206],"measures":[210],"compatibility":[212],"work":[216],"together":[217],"towards":[218],"solving":[219],"sub-problem,":[222],"is":[223],"used":[224],"designing":[226],"Swarm":[229],"(HetSRL)":[231],"algorithm":[232],"HetSs":[235],"intended":[239],"SDMPs.":[240]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}