{"id":"https://openalex.org/W2095564494","doi":"https://doi.org/10.1142/s0219525911002998","title":"AN EMPIRICAL STUDY OF POTENTIAL-BASED REWARD SHAPING AND ADVICE IN COMPLEX, MULTI-AGENT SYSTEMS","display_name":"AN EMPIRICAL STUDY OF POTENTIAL-BASED REWARD SHAPING AND ADVICE IN COMPLEX, MULTI-AGENT SYSTEMS","publication_year":2011,"publication_date":"2011-04-01","ids":{"openalex":"https://openalex.org/W2095564494","doi":"https://doi.org/10.1142/s0219525911002998","mag":"2095564494"},"language":"en","primary_location":{"id":"doi:10.1142/s0219525911002998","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219525911002998","pdf_url":null,"source":{"id":"https://openalex.org/S107361000","display_name":"Advances in Complex Systems","issn_l":"0219-5259","issn":["0219-5259","1793-6802","1793-9615","1793-9623"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Complex Systems","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/A5048451922","display_name":"Sam Devlin","orcid":"https://orcid.org/0000-0002-7769-3090"},"institutions":[{"id":"https://openalex.org/I52099693","display_name":"University of York","ror":"https://ror.org/04m01e293","country_code":"GB","type":"education","lineage":["https://openalex.org/I52099693"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"SAM DEVLIN","raw_affiliation_strings":["University of York, UK","Univ. of York, UK#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of York, UK","institution_ids":["https://openalex.org/I52099693"]},{"raw_affiliation_string":"Univ. of York, UK#TAB#","institution_ids":["https://openalex.org/I52099693"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009587907","display_name":"Daniel Kudenko\u22c6","orcid":"https://orcid.org/0000-0003-3359-3255"},"institutions":[{"id":"https://openalex.org/I52099693","display_name":"University of York","ror":"https://ror.org/04m01e293","country_code":"GB","type":"education","lineage":["https://openalex.org/I52099693"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"DANIEL KUDENKO","raw_affiliation_strings":["University of York, UK","Univ. of York, UK#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of York, UK","institution_ids":["https://openalex.org/I52099693"]},{"raw_affiliation_string":"Univ. of York, UK#TAB#","institution_ids":["https://openalex.org/I52099693"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052315074","display_name":"Marek Grze\u015b","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"MAREK GRZE\u015a","raw_affiliation_strings":["University of Waterloo, CA, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo, CA, Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.9761,"has_fulltext":false,"cited_by_count":80,"citation_normalized_percentile":{"value":0.97646928,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"14","issue":"02","first_page":"251","last_page":"278"},"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/T11252","display_name":"Evolutionary Game Theory and Cooperation","score":0.9869999885559082,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11031","display_name":"Game Theory and Applications","score":0.9793999791145325,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8273867964744568},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.712744414806366},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6063113212585449},{"id":"https://openalex.org/keywords/reward-system","display_name":"Reward system","score":0.5042766332626343},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.48469117283821106},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.48281869292259216},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4564104676246643},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33189624547958374},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.19125095009803772},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.17996880412101746},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11697077751159668}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8273867964744568},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.712744414806366},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6063113212585449},{"id":"https://openalex.org/C143661069","wikidata":"https://www.wikidata.org/wiki/Q670713","display_name":"Reward system","level":2,"score":0.5042766332626343},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.48469117283821106},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.48281869292259216},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4564104676246643},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33189624547958374},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.19125095009803772},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.17996880412101746},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11697077751159668},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1142/s0219525911002998","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219525911002998","pdf_url":null,"source":{"id":"https://openalex.org/S107361000","display_name":"Advances in Complex Systems","issn_l":"0219-5259","issn":["0219-5259","1793-6802","1793-9615","1793-9623"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Complex Systems","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.299.6748","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.299.6748","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.york.ac.uk/aig/papers/devlin-grzes-kudenko-acs2011.pdf","raw_type":"text"},{"id":"pmh:oai:RePEc:wsi:acsxxx:v:14:y:2011:i:02:n:s0219525911002998","is_oa":false,"landing_page_url":"http://www.worldscientific.com/doi/abs/10.1142/S0219525911002998","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:RePEc:wsi:acsxxx:v:14:y:2011:i:02:p:251-278","is_oa":false,"landing_page_url":"http://www.worldscinet.com/cgi-bin/details.cgi?type=html&id=pii:S0219525911002998","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W119236796","https://openalex.org/W1499408472","https://openalex.org/W1553476745","https://openalex.org/W1569296262","https://openalex.org/W1584829138","https://openalex.org/W1593604466","https://openalex.org/W1594783240","https://openalex.org/W1641379095","https://openalex.org/W1641643976","https://openalex.org/W2098432798","https://openalex.org/W2099618002","https://openalex.org/W2100096361","https://openalex.org/W2104602264","https://openalex.org/W2104641222","https://openalex.org/W2105741987","https://openalex.org/W2111316871","https://openalex.org/W2118899043","https://openalex.org/W2119567691","https://openalex.org/W2120846115","https://openalex.org/W2121863487","https://openalex.org/W2123973104","https://openalex.org/W2124175081","https://openalex.org/W2127095112","https://openalex.org/W2129585283","https://openalex.org/W2130750514","https://openalex.org/W2145067550","https://openalex.org/W2145790759","https://openalex.org/W2156194062","https://openalex.org/W2158969944","https://openalex.org/W2164419340","https://openalex.org/W2164851236","https://openalex.org/W2169659168","https://openalex.org/W2171234133","https://openalex.org/W2330024298","https://openalex.org/W2334782222","https://openalex.org/W2482556694","https://openalex.org/W3022194887","https://openalex.org/W3103379718","https://openalex.org/W4214717370","https://openalex.org/W4234761190","https://openalex.org/W6641348789"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W3042900911","https://openalex.org/W2024136090","https://openalex.org/W2964765435"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,30,38,41,47,57,81,102,113],"impact":[4],"of":[5,33,40,49,59],"reward":[6,25,50,65,93],"shaping":[7,26,51,66,94],"in":[8,52],"multi-agent":[9],"reinforcement":[10],"learning":[11,98],"as":[12,72],"a":[13,34,74,107],"way":[14],"to":[15,105],"incorporate":[16],"domain":[17],"knowledge":[18],"about":[19],"good":[20],"strategies.":[21],"In":[22],"theory,":[23],"potential-based":[24],"does":[27],"not":[28],"alter":[29,112],"Nash":[31],"Equilibria":[32],"stochastic":[35],"game,":[36],"only":[37],"exploration":[39],"shaped":[42],"agent.":[43],"We":[44],"demonstrate":[45],"empirically":[46],"performance":[48],"two":[53],"problem":[54],"domains":[55],"within":[56],"context":[58],"RoboCup":[60],"KeepAway":[61],"by":[62],"designing":[63],"three":[64],"schemes,":[67],"encouraging":[68],"specific":[69,87],"behaviour":[70],"such":[71],"keeping":[73],"minimum":[75],"distance":[76],"from":[77],"other":[78],"players":[79],"on":[80,86],"same":[82],"team":[83],"and":[84,110],"taking":[85],"roles.":[88],"The":[89],"results":[90],"illustrate":[91],"that":[92],"with":[95],"multiple,":[96],"simultaneous":[97],"agents":[99],"can":[100,111],"reduce":[101],"time":[103],"needed":[104],"learn":[106],"suitable":[108],"policy":[109],"final":[114],"group":[115],"performance.":[116]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":13},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}