{"id":"https://openalex.org/W2103986944","doi":"https://doi.org/10.1145/1329125.1329412","title":"Advice taking in multiagent reinforcement learning","display_name":"Advice taking in multiagent reinforcement learning","publication_year":2007,"publication_date":"2007-05-14","ids":{"openalex":"https://openalex.org/W2103986944","doi":"https://doi.org/10.1145/1329125.1329412","mag":"2103986944"},"language":"en","primary_location":{"id":"doi:10.1145/1329125.1329412","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1329125.1329412","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th international joint conference on Autonomous agents and multiagent systems","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/A5004220968","display_name":"Michael Rovatsos","orcid":"https://orcid.org/0000-0003-2517-6283"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Michael Rovatsos","raw_affiliation_strings":["The University of Edinburgh, Edinburgh, United Kingdom","The University of Edinburgh, Edinburgh, United Kingdom;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"The University of Edinburgh, Edinburgh, United Kingdom;","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052964303","display_name":"Alexandros Belesiotis","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alexandros Belesiotis","raw_affiliation_strings":["The University of Edinburgh, Edinburgh, United Kingdom","The University of Edinburgh, Edinburgh, United Kingdom;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"The University of Edinburgh, Edinburgh, United Kingdom;","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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":0.9991999864578247,"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/T11031","display_name":"Game Theory and Applications","score":0.9979000091552734,"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"}},{"id":"https://openalex.org/T11252","display_name":"Evolutionary Game Theory and Cooperation","score":0.9912999868392944,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9105247259140015},{"id":"https://openalex.org/keywords/advice","display_name":"Advice (programming)","score":0.8754897117614746},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7215767502784729},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.5916052460670471},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5542793869972229},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5486937761306763},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5320649743080139},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.4690713584423065},{"id":"https://openalex.org/keywords/marl","display_name":"Marl","score":0.4393150806427002},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10138028860092163},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.06843811273574829},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06739488244056702}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9105247259140015},{"id":"https://openalex.org/C2779955035","wikidata":"https://www.wikidata.org/wiki/Q4686785","display_name":"Advice (programming)","level":2,"score":0.8754897117614746},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7215767502784729},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.5916052460670471},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5542793869972229},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5486937761306763},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5320649743080139},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.4690713584423065},{"id":"https://openalex.org/C92927620","wikidata":"https://www.wikidata.org/wiki/Q184053","display_name":"Marl","level":3,"score":0.4393150806427002},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10138028860092163},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.06843811273574829},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06739488244056702},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C109007969","wikidata":"https://www.wikidata.org/wiki/Q749565","display_name":"Structural basin","level":2,"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":3,"locations":[{"id":"doi:10.1145/1329125.1329412","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1329125.1329412","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th international joint conference on Autonomous agents and multiagent systems","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.206.1199","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.206.1199","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://homepages.inf.ed.ac.uk/mrovatso/papers/rovatsosetal-aamas2007-long.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.206.891","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.206.891","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://homepages.inf.ed.ac.uk/mrovatso/papers/rovatsosetal-aamas2007.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1513468570","https://openalex.org/W1515851193","https://openalex.org/W1542941925","https://openalex.org/W1815493548","https://openalex.org/W2103561211","https://openalex.org/W2104602264","https://openalex.org/W2118899043","https://openalex.org/W2120327309","https://openalex.org/W2121863487","https://openalex.org/W2134112261","https://openalex.org/W2138362680","https://openalex.org/W2164637474","https://openalex.org/W2911283634","https://openalex.org/W2914656440","https://openalex.org/W2951054971","https://openalex.org/W4214717370","https://openalex.org/W6689723076"],"related_works":["https://openalex.org/W2126019709","https://openalex.org/W1702901972","https://openalex.org/W4249798507","https://openalex.org/W2069775250","https://openalex.org/W2093541819","https://openalex.org/W2032294417","https://openalex.org/W2152754392","https://openalex.org/W1989172970","https://openalex.org/W2196316523","https://openalex.org/W1899363654"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"the":[3,31,40,52,65,87],"\u03b2-WoLF":[4,26],"algorithm":[5,33,76],"for":[6,51],"multiagent":[7],"reinforcement":[8],"learning":[9,53],"(MARL)":[10],"that":[11,34,79],"uses":[12],"an":[13,28],"additional":[14,45],"\"advice\"":[15],"signal":[16,47],"to":[17,37,89],"inform":[18],"agents":[19,36,63],"about":[20],"mutually":[21],"beneficial":[22],"forms":[23],"of":[24,30],"behaviour.":[25],"is":[27,48],"extension":[29],"WoLF-PHC":[32],"allows":[35],"assess":[38],"whether":[39],"advice":[41],"obtained":[42,72],"through":[43],"this":[44,74],"reward":[46],"(i)":[49],"useful":[50],"agent":[54],"itself":[55],"and":[56],"(ii)":[57],"currently":[58],"being":[59],"followed":[60],"by":[61],"other":[62],"in":[64,83,85,95],"system.":[66],"We":[67],"report":[68],"on":[69],"experimental":[70],"results":[71,94],"with":[73],"novel":[75],"which":[77,86],"indicate":[78],"it":[80],"enables":[81],"cooperation":[82],"scenarios":[84],"need":[88],"defend":[90],"oneself":[91],"against":[92],"exploitation":[93],"poor":[96],"coordination":[97],"using":[98],"existing":[99],"MARL":[100],"algorithms.":[101]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}