{"id":"https://openalex.org/W3004047001","doi":"https://doi.org/10.24963/ijcai.2020/42","title":"A Deep Reinforcement Learning Approach to Concurrent Bilateral Negotiation","display_name":"A Deep Reinforcement Learning Approach to Concurrent Bilateral Negotiation","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3004047001","doi":"https://doi.org/10.24963/ijcai.2020/42","mag":"3004047001"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2020/42","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/42","pdf_url":"https://www.ijcai.org/proceedings/2020/0042.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2020/0042.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091297166","display_name":"Pallavi Bagga","orcid":"https://orcid.org/0000-0001-5226-1948"},"institutions":[{"id":"https://openalex.org/I184558857","display_name":"Royal Holloway University of London","ror":"https://ror.org/04g2vpn86","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I184558857"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Pallavi Bagga","raw_affiliation_strings":["Royal Holloway, University of London, UK","Royal Holloway University of London, UK,"],"affiliations":[{"raw_affiliation_string":"Royal Holloway, University of London, UK","institution_ids":["https://openalex.org/I184558857"]},{"raw_affiliation_string":"Royal Holloway University of London, UK,","institution_ids":["https://openalex.org/I184558857"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016140478","display_name":"Nicola Paoletti","orcid":"https://orcid.org/0000-0002-4723-5363"},"institutions":[{"id":"https://openalex.org/I184558857","display_name":"Royal Holloway University of London","ror":"https://ror.org/04g2vpn86","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I184558857"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nicola Paoletti","raw_affiliation_strings":["Royal Holloway, University of London, UK","Royal Holloway University of London, UK,"],"affiliations":[{"raw_affiliation_string":"Royal Holloway, University of London, UK","institution_ids":["https://openalex.org/I184558857"]},{"raw_affiliation_string":"Royal Holloway University of London, UK,","institution_ids":["https://openalex.org/I184558857"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054616935","display_name":"Bedour Alrayes","orcid":null},"institutions":[{"id":"https://openalex.org/I28022161","display_name":"King Saud University","ror":"https://ror.org/02f81g417","country_code":"SA","type":"education","lineage":["https://openalex.org/I28022161"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Bedour Alrayes","raw_affiliation_strings":["King Saud University, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"King Saud University, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035046930","display_name":"Kostas Stathis","orcid":"https://orcid.org/0000-0002-9946-4037"},"institutions":[{"id":"https://openalex.org/I184558857","display_name":"Royal Holloway University of London","ror":"https://ror.org/04g2vpn86","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I184558857"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kostas Stathis","raw_affiliation_strings":["Royal Holloway, University of London, UK","Royal Holloway University of London, UK,"],"affiliations":[{"raw_affiliation_string":"Royal Holloway, University of London, UK","institution_ids":["https://openalex.org/I184558857"]},{"raw_affiliation_string":"Royal Holloway University of London, UK,","institution_ids":["https://openalex.org/I184558857"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5091297166"],"corresponding_institution_ids":["https://openalex.org/I184558857"],"apc_list":null,"apc_paid":null,"fwci":0.73429774,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.74824029,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"297","last_page":"303"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9988999962806702,"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":0.9988999962806702,"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/T11182","display_name":"Auction Theory and Applications","score":0.9940999746322632,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9890000224113464,"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/negotiation","display_name":"Negotiation","score":0.940618097782135},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9180585145950317},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7367725372314453},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5379451513290405},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5302925705909729},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.43699929118156433},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.41435861587524414},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11916446685791016},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.08519837260246277},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.06864294409751892},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.06519880890846252}],"concepts":[{"id":"https://openalex.org/C199776023","wikidata":"https://www.wikidata.org/wiki/Q202875","display_name":"Negotiation","level":2,"score":0.940618097782135},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9180585145950317},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7367725372314453},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5379451513290405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5302925705909729},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.43699929118156433},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.41435861587524414},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11916446685791016},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.08519837260246277},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.06864294409751892},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.06519880890846252},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.24963/ijcai.2020/42","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/42","pdf_url":"https://www.ijcai.org/proceedings/2020/0042.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2001.11785","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.11785","pdf_url":"https://arxiv.org/pdf/2001.11785","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"mag:3004047001","is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2001.11785.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2001.11785","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2001.11785","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2020/42","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/42","pdf_url":"https://www.ijcai.org/proceedings/2020/0042.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3004047001.pdf","grobid_xml":"https://content.openalex.org/works/W3004047001.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W84256470","https://openalex.org/W1554291173","https://openalex.org/W1886567659","https://openalex.org/W2009139311","https://openalex.org/W2031075655","https://openalex.org/W2105440797","https://openalex.org/W2112374372","https://openalex.org/W2113952909","https://openalex.org/W2139512434","https://openalex.org/W2153672931","https://openalex.org/W2159477762","https://openalex.org/W2167957569","https://openalex.org/W2173248099","https://openalex.org/W2485373136","https://openalex.org/W2557283755","https://openalex.org/W2625113742","https://openalex.org/W2765464748","https://openalex.org/W2884122151","https://openalex.org/W2892340158","https://openalex.org/W2896469545","https://openalex.org/W2946012239","https://openalex.org/W6603372080","https://openalex.org/W6834709193"],"related_works":["https://openalex.org/W3035596831","https://openalex.org/W3166105432","https://openalex.org/W2367524689","https://openalex.org/W2370674770","https://openalex.org/W2765464748","https://openalex.org/W3045508234","https://openalex.org/W2001907002","https://openalex.org/W385183578","https://openalex.org/W2387890110","https://openalex.org/W2946012239","https://openalex.org/W84256470","https://openalex.org/W2380817166","https://openalex.org/W1026401282","https://openalex.org/W2060331105","https://openalex.org/W2398925187","https://openalex.org/W69294083","https://openalex.org/W17839413","https://openalex.org/W273841654","https://openalex.org/W2254572654","https://openalex.org/W2027638851"],"abstract_inverted_index":{"We":[0,44],"present":[1],"a":[2,36,40,65,111],"novel":[3],"negotiation":[4,103],"model":[5],"that":[6,75,92],"allows":[7],"an":[8,27],"agent":[9,25],"to":[10,13,34,78,85],"learn":[11,35],"how":[12],"negotiate":[14],"during":[15,62],"concurrent":[16,73,107],"bilateral":[17,108],"negotiations":[18,74,109],"in":[19,105],"unknown":[20],"and":[21],"dynamic":[22],"e-markets.":[23],"The":[24],"uses":[26],"actor-critic":[28],"architecture":[29],"with":[30],"model-free":[31],"reinforcement":[32,95],"learning":[33,61,96],"strategy":[37,47],"expressed":[38],"as":[39],"deep":[41,94],"neural":[42],"network.":[43],"pre-train":[45],"the":[46,56,83],"by":[48],"supervision":[49],"from":[50],"synthetic":[51],"market":[52],"data,":[53],"thereby":[54],"decreasing":[55],"exploration":[57],"time":[58],"required":[59],"for":[60,72,110],"negotiation.":[63],"As":[64],"result,":[66],"we":[67],"can":[68,76],"build":[69],"automated":[70],"agents":[71,98],"adapt":[77],"different":[79],"e-market":[80,114],"settings":[81],"without":[82],"need":[84],"be":[86],"pre-programmed.":[87],"Our":[88],"experimental":[89],"evaluation":[90],"shows":[91],"our":[93],"based":[97],"outperform":[99],"two":[100],"existing":[101],"well-known":[102],"strategies":[104],"one-to-many":[106],"range":[112],"of":[113],"settings.":[115]},"counts_by_year":[{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}