{"id":"https://openalex.org/W2174703168","doi":"https://doi.org/10.18653/v1/w15-4605","title":"Reinforcement Learning in Multi-Party Trading Dialog","display_name":"Reinforcement Learning in Multi-Party Trading Dialog","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2174703168","doi":"https://doi.org/10.18653/v1/w15-4605","mag":"2174703168"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w15-4605","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-4605","pdf_url":"https://www.aclweb.org/anthology/W15-4605.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W15-4605.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064754457","display_name":"T. HIRAOKA","orcid":"https://orcid.org/0000-0002-4755-8816"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Takuya Hiraoka","raw_affiliation_strings":["Nara Institute of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112401163","display_name":"Kallirroi Georgila","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087747","display_name":"Creative Technologies (United States)","ror":"https://ror.org/001qkb777","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087747"]},{"id":"https://openalex.org/I4388482679","display_name":"USC Institute for Creative Technologies","ror":"https://ror.org/03hjhvn29","country_code":null,"type":"facility","lineage":["https://openalex.org/I1174212","https://openalex.org/I4388482679"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kallirroi Georgila","raw_affiliation_strings":["USC Institute for Creative Technologies"],"affiliations":[{"raw_affiliation_string":"USC Institute for Creative Technologies","institution_ids":["https://openalex.org/I4210087747","https://openalex.org/I4388482679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037183302","display_name":"Elnaz Nouri","orcid":null},"institutions":[{"id":"https://openalex.org/I4388482679","display_name":"USC Institute for Creative Technologies","ror":"https://ror.org/03hjhvn29","country_code":null,"type":"facility","lineage":["https://openalex.org/I1174212","https://openalex.org/I4388482679"]},{"id":"https://openalex.org/I4210087747","display_name":"Creative Technologies (United States)","ror":"https://ror.org/001qkb777","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087747"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elnaz Nouri","raw_affiliation_strings":["USC Institute for Creative Technologies"],"affiliations":[{"raw_affiliation_string":"USC Institute for Creative Technologies","institution_ids":["https://openalex.org/I4210087747","https://openalex.org/I4388482679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004384107","display_name":"David Traum","orcid":null},"institutions":[{"id":"https://openalex.org/I4388482679","display_name":"USC Institute for Creative Technologies","ror":"https://ror.org/03hjhvn29","country_code":null,"type":"facility","lineage":["https://openalex.org/I1174212","https://openalex.org/I4388482679"]},{"id":"https://openalex.org/I4210087747","display_name":"Creative Technologies (United States)","ror":"https://ror.org/001qkb777","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087747"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Traum","raw_affiliation_strings":["USC Institute for Creative Technologies"],"affiliations":[{"raw_affiliation_string":"USC Institute for Creative Technologies","institution_ids":["https://openalex.org/I4210087747","https://openalex.org/I4388482679"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Nakamura","raw_affiliation_strings":["Nara Institute of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5064754457"],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":2.6706,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.91835723,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"32","last_page":"41"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9997000098228455,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9997000098228455,"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/T12031","display_name":"Speech and dialogue systems","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/T10028","display_name":"Topic Modeling","score":0.9940999746322632,"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/dialog-box","display_name":"Dialog box","score":0.9588192701339722},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9277148246765137},{"id":"https://openalex.org/keywords/negotiation","display_name":"Negotiation","score":0.8518953323364258},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8385518789291382},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5829237699508667},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.521969199180603},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5169738531112671},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3573068678379059},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.09245896339416504}],"concepts":[{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.9588192701339722},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9277148246765137},{"id":"https://openalex.org/C199776023","wikidata":"https://www.wikidata.org/wiki/Q202875","display_name":"Negotiation","level":2,"score":0.8518953323364258},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8385518789291382},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5829237699508667},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.521969199180603},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5169738531112671},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3573068678379059},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.09245896339416504},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/w15-4605","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-4605","pdf_url":"https://www.aclweb.org/anthology/W15-4605.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.705.1884","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.705.1884","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://people.ict.usc.edu/%7Ekgeorgila/publications/hiraoka_sigdial15.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.988.2804","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.988.2804","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://anthology.aclweb.org/W/W15/W15-4605.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.988.8042","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.988.8042","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ict.usc.edu/pubs/Reinforcement%20Learning%20in%20Multi-Party%20Trading%20Dialog.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.18653/v1/w15-4605","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-4605","pdf_url":"https://www.aclweb.org/anthology/W15-4605.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1069223013","display_name":null,"funder_award_id":"JSPS KAKENHI","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G2595913501","display_name":null,"funder_award_id":"JSPS KAKENHI","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3459562248","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3807043894","display_name":"\u7570\u7fc5\u4e9c\u76ee\u306b\u5c5e\u3059\u308b\u6606\u866b\u306e\u67d3\u8272\u4f53\u7814\u7a76","funder_award_id":"24003","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4227499671","display_name":null,"funder_award_id":"KAKENHI Grant","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4636223006","display_name":null,"funder_award_id":"JSPS KAK","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G5786340949","display_name":null,"funder_award_id":"KAKENHI Grant Number","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7578374220","display_name":null,"funder_award_id":"24240032","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7698864405","display_name":"EAGER: Reinforcement Learning of Multi-Party Negotiation Dialogue Policies","funder_award_id":"1450656","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7752643416","display_name":null,"funder_award_id":"Japan","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8430481527","display_name":null,"funder_award_id":"Number","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320324891","display_name":"Iran Telecommunication Research Center","ror":"https://ror.org/01a3g2z22"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320335839","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2174703168.pdf","grobid_xml":"https://content.openalex.org/works/W2174703168.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W143053999","https://openalex.org/W147203046","https://openalex.org/W166862392","https://openalex.org/W1506513758","https://openalex.org/W1524881148","https://openalex.org/W1593204419","https://openalex.org/W1777239053","https://openalex.org/W2009139311","https://openalex.org/W2033921274","https://openalex.org/W2115714256","https://openalex.org/W2121863487","https://openalex.org/W2132997613","https://openalex.org/W2136152952","https://openalex.org/W2142831953","https://openalex.org/W2143435603","https://openalex.org/W2152342063","https://openalex.org/W2153672931","https://openalex.org/W2231198303","https://openalex.org/W2246008130","https://openalex.org/W2251854674","https://openalex.org/W2294062087","https://openalex.org/W2312609093","https://openalex.org/W2323798077","https://openalex.org/W2438667436","https://openalex.org/W2586680856","https://openalex.org/W2970208590","https://openalex.org/W3099293669","https://openalex.org/W4205363819","https://openalex.org/W4214717370","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2098987383","https://openalex.org/W2417260800","https://openalex.org/W1596203174","https://openalex.org/W2117933979","https://openalex.org/W2283130723","https://openalex.org/W103938586","https://openalex.org/W2104718772","https://openalex.org/W4233992201","https://openalex.org/W2368721880","https://openalex.org/W2174703168"],"abstract_inverted_index":{"In":[0,49],"this":[1],"paper,":[2],"we":[3,52],"apply":[4],"reinforcement":[5],"learning":[6,84],"(RL)":[7],"to":[8],"a":[9,90],"multi-party":[10,80],"trading":[11,81],"scenario":[12],"where":[13],"the":[14,39,55,58,63,68,96,118],"dialog":[15,45,82],"system":[16],"(learner)":[17],"trades":[18],"with":[19,28,46,104],"one,":[20],"two,":[21],"or":[22,114],"three":[23],"other":[24],"agents.":[25],"We":[26],"experiment":[27],"different":[29],"RL":[30,64],"algorithms":[31],"and":[32,67,94],"reward":[33,107],"functions.":[34],"The":[35],"negotiation":[36,87,110],"strategy":[37],"of":[38,57,70,98,120],"learner":[40,59],"is":[41,89],"learned":[42],"through":[43],"simulated":[44],"trader":[47],"simulators.":[48],"our":[50],"experiments,":[51],"evaluate":[53],"how":[54],"performance":[56],"varies":[60],"depending":[61],"on":[62],"algorithm":[65],"used":[66],"number":[69],"traders.":[71],"Our":[72],"results":[73],"show":[74],"that":[75],"(1)":[76],"even":[77,115],"in":[78],"simple":[79],"tasks,":[83],"an":[85,105],"effective":[86,113],"policy":[88],"very":[91],"hard":[92],"problem;":[93],"(2)":[95],"use":[97],"neural":[99],"fitted":[100],"Q":[101],"iteration":[102],"combined":[103],"incremental":[106],"function":[108],"produces":[109],"policies":[111,119],"as":[112],"better":[116],"than":[117],"two":[121],"strong":[122],"hand-crafted":[123],"baselines.":[124]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2018,"cited_by_count":5},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
