{"id":"https://openalex.org/W2154674083","doi":"https://doi.org/10.1109/ijcnn.2004.1380087","title":"Asymmetric multiagent reinforcement learning in pricing applications","display_name":"Asymmetric multiagent reinforcement learning in pricing applications","publication_year":2005,"publication_date":"2005-04-05","ids":{"openalex":"https://openalex.org/W2154674083","doi":"https://doi.org/10.1109/ijcnn.2004.1380087","mag":"2154674083"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2004.1380087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2004.1380087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541)","raw_type":"proceedings-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/A5065253727","display_name":"Ville K\u00f6n\u00f6nen","orcid":null},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"V. Kononen","raw_affiliation_strings":["Neural Networks Research Centre, Hut, Helsinki University of Technology, Finland"],"affiliations":[{"raw_affiliation_string":"Neural Networks Research Centre, Hut, Helsinki University of Technology, Finland","institution_ids":["https://openalex.org/I133731052"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085424325","display_name":"Erkki Oja","orcid":null},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"E. Oja","raw_affiliation_strings":["Neural Networks Research Centre, Hut, Helsinki University of Technology, Finland"],"affiliations":[{"raw_affiliation_string":"Neural Networks Research Centre, Hut, Helsinki University of Technology, Finland","institution_ids":["https://openalex.org/I133731052"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5065253727"],"corresponding_institution_ids":["https://openalex.org/I133731052"],"apc_list":null,"apc_paid":null,"fwci":0.8775,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.81495783,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"2","issue":null,"first_page":"1097","last_page":"1102"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.973800003528595,"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":0.973800003528595,"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":0.9732000231742859,"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/T11182","display_name":"Auction Theory and Applications","score":0.9681000113487244,"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":0.9274933338165283},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7121052742004395},{"id":"https://openalex.org/keywords/dynamic-pricing","display_name":"Dynamic pricing","score":0.4682503640651703},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.45846307277679443},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.44840550422668457},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.438811719417572},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.42513343691825867},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3558804988861084},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.34947097301483154},{"id":"https://openalex.org/keywords/microeconomics","display_name":"Microeconomics","score":0.23393908143043518},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.18939781188964844},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.13252022862434387},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08009299635887146}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9274933338165283},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7121052742004395},{"id":"https://openalex.org/C2779391423","wikidata":"https://www.wikidata.org/wiki/Q17009728","display_name":"Dynamic pricing","level":2,"score":0.4682503640651703},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.45846307277679443},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.44840550422668457},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.438811719417572},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.42513343691825867},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3558804988861084},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.34947097301483154},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.23393908143043518},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.18939781188964844},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.13252022862434387},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08009299635887146},{"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:10.1109/ijcnn.2004.1380087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2004.1380087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W572414231","https://openalex.org/W1483825349","https://openalex.org/W1502765764","https://openalex.org/W1513468570","https://openalex.org/W1579312135","https://openalex.org/W1589560630","https://openalex.org/W1598756869","https://openalex.org/W1780505730","https://openalex.org/W2006660022","https://openalex.org/W2073946526","https://openalex.org/W4249236604","https://openalex.org/W4285719527","https://openalex.org/W6630520071","https://openalex.org/W6635954354","https://openalex.org/W6638148280","https://openalex.org/W6831055800"],"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/W4284974072","https://openalex.org/W2341346307","https://openalex.org/W4225269853"],"abstract_inverted_index":{"Two":[0],"pricing":[1,21,47,77,93],"problems":[2,94],"are":[3,24],"solved":[4],"by":[5],"using":[6],"asymmetric":[7],"multiagent":[8,97],"reinforcement":[9,81,98],"learning":[10],"methods":[11,62],"in":[12],"this":[13],"paper.":[14],"In":[15,58],"the":[16,37,61,84],"first":[17],"problem,":[18],"a":[19,45,50,72],"flat":[20],"scenario,":[22,48],"there":[23],"two":[25,55,92],"competing":[26,56],"brokers":[27],"that":[28],"sell":[29],"identical":[30],"products":[31,53],"to":[32,54,66],"customers":[33],"and":[34,64,90],"compete":[35],"on":[36,80,96],"basis":[38],"of":[39,76,87],"price.":[40],"The":[41],"second":[42],"problem":[43],"is":[44],"hierarchical":[46],"where":[49],"supplier":[51],"sells":[52],"brokers.":[57],"both":[59],"cases,":[60],"converged":[63],"led":[65],"very":[67],"promising":[68],"results.":[69],"We":[70],"present":[71],"brief":[73],"literature":[74],"survey":[75],"models":[78],"based":[79,95],"learning,":[82],"introduce":[83],"basic":[85],"concepts":[86],"Markov":[88],"games":[89],"solve":[91],"learning.":[99]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}