{"id":"https://openalex.org/W2902922568","doi":"https://doi.org/10.1017/s0269888918000292","title":"Reward shaping for knowledge-based multi-objective multi-agent reinforcement learning","display_name":"Reward shaping for knowledge-based multi-objective multi-agent reinforcement learning","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2902922568","doi":"https://doi.org/10.1017/s0269888918000292","mag":"2902922568"},"language":"en","primary_location":{"id":"doi:10.1017/s0269888918000292","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s0269888918000292","pdf_url":null,"source":{"id":"https://openalex.org/S137506714","display_name":"The Knowledge Engineering Review","issn_l":"0269-8889","issn":["0269-8889","1469-8005"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Knowledge Engineering Review","raw_type":"journal-article"},"type":"article","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/A5046330057","display_name":"Patrick Mannion","orcid":"https://orcid.org/0000-0002-7951-878X"},"institutions":[{"id":"https://openalex.org/I63871047","display_name":"Galway-Mayo Institute of Technology","ror":"https://ror.org/024j9sx72","country_code":"IE","type":"education","lineage":["https://openalex.org/I63871047"]}],"countries":["IE"],"is_corresponding":true,"raw_author_name":"Patrick Mannion","raw_affiliation_strings":["Department of Computer Science & Applied Physics, Galway-Mayo Institute of Technology, Dublin Road, GalwayH91 T8NW, Ireland; e-mail:","Department of Computer Science & Applied Physics, Galway-Mayo Institute of Technology, Dublin Road, GalwayH91 T8NW, Ireland","e-mail:"],"raw_orcid":"https://orcid.org/0000-0002-7951-878X","affiliations":[{"raw_affiliation_string":"Department of Computer Science & Applied Physics, Galway-Mayo Institute of Technology, Dublin Road, GalwayH91 T8NW, Ireland; e-mail:","institution_ids":["https://openalex.org/I63871047"]},{"raw_affiliation_string":"Department of Computer Science & Applied Physics, Galway-Mayo Institute of Technology, Dublin Road, GalwayH91 T8NW, Ireland","institution_ids":["https://openalex.org/I63871047"]},{"raw_affiliation_string":"e-mail:","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048451922","display_name":"Sam Devlin","orcid":"https://orcid.org/0000-0002-7769-3090"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sam Devlin","raw_affiliation_strings":["Microsoft Research, 21 Station Road, CambridgeCB1 2FB, United Kingdom; e-mail:","e-mail:","Microsoft Research, 21 Station Road, CambridgeCB1 2FB, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, 21 Station Road, CambridgeCB1 2FB, United Kingdom; e-mail:","institution_ids":["https://openalex.org/I4210164937"]},{"raw_affiliation_string":"e-mail:","institution_ids":[]},{"raw_affiliation_string":"Microsoft Research, 21 Station Road, CambridgeCB1 2FB, United Kingdom","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031508546","display_name":"Jim Duggan","orcid":"https://orcid.org/0000-0002-7507-8617"},"institutions":[{"id":"https://openalex.org/I188760350","display_name":"Ollscoil na Gaillimhe \u2013 University of Galway","ror":"https://ror.org/03bea9k73","country_code":"IE","type":"education","lineage":["https://openalex.org/I188760350"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Jim Duggan","raw_affiliation_strings":["Discipline of Information Technology, National University of Ireland Galway, GalwayH91 TK33, Ireland; e-mail:","Discipline of Information Technology, National University of Ireland Galway, GalwayH91 TK33, Ireland","e-mail:"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Discipline of Information Technology, National University of Ireland Galway, GalwayH91 TK33, Ireland; e-mail:","institution_ids":["https://openalex.org/I188760350"]},{"raw_affiliation_string":"Discipline of Information Technology, National University of Ireland Galway, GalwayH91 TK33, Ireland","institution_ids":["https://openalex.org/I188760350"]},{"raw_affiliation_string":"e-mail:","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074452240","display_name":"Enda Howley","orcid":"https://orcid.org/0000-0003-2687-4630"},"institutions":[{"id":"https://openalex.org/I188760350","display_name":"Ollscoil na Gaillimhe \u2013 University of Galway","ror":"https://ror.org/03bea9k73","country_code":"IE","type":"education","lineage":["https://openalex.org/I188760350"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Enda Howley","raw_affiliation_strings":["Discipline of Information Technology, National University of Ireland Galway, GalwayH91 TK33, Ireland; e-mail:","e-mail:","Discipline of Information Technology, National University of Ireland Galway, GalwayH91 TK33, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Discipline of Information Technology, National University of Ireland Galway, GalwayH91 TK33, Ireland; e-mail:","institution_ids":["https://openalex.org/I188760350"]},{"raw_affiliation_string":"e-mail:","institution_ids":[]},{"raw_affiliation_string":"Discipline of Information Technology, National University of Ireland Galway, GalwayH91 TK33, Ireland","institution_ids":["https://openalex.org/I188760350"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5046330057"],"corresponding_institution_ids":["https://openalex.org/I63871047"],"apc_list":null,"apc_paid":null,"fwci":2.8775,"has_fulltext":false,"cited_by_count":64,"citation_normalized_percentile":{"value":0.92904093,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"33","issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9977999925613403,"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":0.9977999925613403,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9901000261306763,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9771000146865845,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8312195539474487},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7096775770187378},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6490296125411987},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.5574135780334473},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4936434030532837},{"id":"https://openalex.org/keywords/unintended-consequences","display_name":"Unintended consequences","score":0.4894675016403198},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4289632737636566},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42655789852142334},{"id":"https://openalex.org/keywords/pareto-principle","display_name":"Pareto principle","score":0.4193897247314453},{"id":"https://openalex.org/keywords/management-science","display_name":"Management science","score":0.3315611481666565},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.26624956727027893},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.19594994187355042},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12810856103897095},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.11557409167289734},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.09077244997024536}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8312195539474487},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7096775770187378},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6490296125411987},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5574135780334473},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4936434030532837},{"id":"https://openalex.org/C2776889888","wikidata":"https://www.wikidata.org/wiki/Q1135789","display_name":"Unintended consequences","level":2,"score":0.4894675016403198},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4289632737636566},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42655789852142334},{"id":"https://openalex.org/C137635306","wikidata":"https://www.wikidata.org/wiki/Q182667","display_name":"Pareto principle","level":2,"score":0.4193897247314453},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.3315611481666565},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.26624956727027893},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.19594994187355042},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12810856103897095},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.11557409167289734},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.09077244997024536},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1017/s0269888918000292","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s0269888918000292","pdf_url":null,"source":{"id":"https://openalex.org/S137506714","display_name":"The Knowledge Engineering Review","issn_l":"0269-8889","issn":["0269-8889","1469-8005"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Knowledge Engineering Review","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W98348426","https://openalex.org/W119236796","https://openalex.org/W177268831","https://openalex.org/W206679605","https://openalex.org/W638247099","https://openalex.org/W1499408472","https://openalex.org/W1562694074","https://openalex.org/W1575989700","https://openalex.org/W1586030051","https://openalex.org/W1777239053","https://openalex.org/W1966554507","https://openalex.org/W1969302761","https://openalex.org/W1980358463","https://openalex.org/W1982239148","https://openalex.org/W1997188340","https://openalex.org/W1999371911","https://openalex.org/W2000148779","https://openalex.org/W2001773141","https://openalex.org/W2012612381","https://openalex.org/W2057057119","https://openalex.org/W2060846151","https://openalex.org/W2064774485","https://openalex.org/W2082607648","https://openalex.org/W2095564494","https://openalex.org/W2101786389","https://openalex.org/W2102660061","https://openalex.org/W2104602264","https://openalex.org/W2117428849","https://openalex.org/W2139218382","https://openalex.org/W2145790759","https://openalex.org/W2151382427","https://openalex.org/W2156194062","https://openalex.org/W2163526437","https://openalex.org/W2182714085","https://openalex.org/W2186820913","https://openalex.org/W2189058185","https://openalex.org/W2324612253","https://openalex.org/W2330024298","https://openalex.org/W2410877381","https://openalex.org/W2480177474","https://openalex.org/W2480989315","https://openalex.org/W2509924317","https://openalex.org/W2519114575","https://openalex.org/W2620974420","https://openalex.org/W2625366419","https://openalex.org/W2753100091","https://openalex.org/W3103262232","https://openalex.org/W3123344192","https://openalex.org/W3140017782","https://openalex.org/W4234761190","https://openalex.org/W6634489592","https://openalex.org/W6806676947"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2120447654","https://openalex.org/W2977179488","https://openalex.org/W2130974462","https://openalex.org/W972276598","https://openalex.org/W2144453115","https://openalex.org/W2028665553","https://openalex.org/W2086519370"],"abstract_inverted_index":{"Abstract":[0],"The":[1],"majority":[2],"of":[3,50,80,113,129],"multi-agent":[4],"reinforcement":[5],"learning":[6,108],"(MARL)":[7],"implementations":[8],"aim":[9],"to":[10,15,43,61,75,86,106,134],"optimize":[11],"systems":[12],"with":[13,47],"respect":[14],"a":[16,59,81],"single":[17],"objective,":[18],"despite":[19],"the":[20,48,63,77,111,126,150],"fact":[21],"that":[22,154],"many":[23],"real-world":[24],"problems":[25],"are":[26,93],"inherently":[27],"multi-objective":[28,33,136,168],"in":[29,37,67,119,166],"nature.":[30],"Research":[31],"into":[32],"MARL":[34,121,137],"is":[35],"still":[36],"its":[38],"infancy,":[39],"and":[40,97,100,110,139],"few":[41],"studies":[42],"date":[44],"have":[45,102],"dealt":[46],"issue":[49],"credit":[51,64],"assignment.":[52],"Reward":[53],"shaping":[54,91,96,132,158],"has":[55,72],"been":[56,73,103],"proposed":[57],"as":[58],"means":[60],"address":[62],"assignment":[65],"problem":[66],"single-objective":[68,120],"MARL,":[69],"however":[70],"it":[71],"shown":[74,105],"alter":[76],"intended":[78],"goals":[79],"domain":[82],"if":[83],"misused,":[84],"leading":[85],"unintended":[87],"behaviour.":[88],"Two":[89],"popular":[90],"methods":[92],"potential-based":[94],"reward":[95],"difference":[98],"rewards,":[99],"both":[101],"repeatedly":[104],"improve":[107],"speed":[109],"quality":[112],"joint":[114],"policies":[115],"learned":[116],"by":[117],"agents":[118,155],"domains.":[122,146],"This":[123],"work":[124],"discusses":[125],"theoretical":[127],"implications":[128],"applying":[130],"these":[131,157],"approaches":[133],"cooperative":[135,167],"problems,":[138],"evaluates":[140],"their":[141],"efficacy":[142],"using":[143,156],"two":[144],"benchmark":[145],"Our":[147],"results":[148],"constitute":[149],"first":[151],"empirical":[152],"evidence":[153],"methodologies":[159],"can":[160],"sample":[161],"true":[162],"Pareto":[163],"optimal":[164],"solutions":[165],"stochastic":[169],"games.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2026-05-14T08:36:36.166977","created_date":"2025-10-10T00:00:00"}