{"id":"https://openalex.org/W3167696941","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533817","title":"A Reward Shaping Approach for Reserve Price Optimization using Deep Reinforcement Learning","display_name":"A Reward Shaping Approach for Reserve Price Optimization using Deep Reinforcement Learning","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3167696941","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533817","mag":"3167696941"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9533817","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533817","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pure.tue.nl/ws/files/172689328/ijcnn_camera_ready.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019907650","display_name":"Reza Refaei Afshar","orcid":null},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Reza Refaei Afshar","raw_affiliation_strings":["Eindhoven University of Technology,Eindhoven,The Netherlands","Eindhoven University of Technology, Eindhoven, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology,Eindhoven,The Netherlands","institution_ids":["https://openalex.org/I83019370"]},{"raw_affiliation_string":"Eindhoven University of Technology, Eindhoven, The Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062973890","display_name":"Jason Rhuggenaath","orcid":"https://orcid.org/0000-0001-5368-2947"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Jason Rhuggenaath","raw_affiliation_strings":["Eindhoven University of Technology,Eindhoven,The Netherlands","Eindhoven University of Technology, Eindhoven, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology,Eindhoven,The Netherlands","institution_ids":["https://openalex.org/I83019370"]},{"raw_affiliation_string":"Eindhoven University of Technology, Eindhoven, The Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077147157","display_name":"Yingqian Zhang","orcid":"https://orcid.org/0000-0002-5073-0787"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Yingqian Zhang","raw_affiliation_strings":["Eindhoven University of Technology,Eindhoven,The Netherlands","Eindhoven University of Technology, Eindhoven, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology,Eindhoven,The Netherlands","institution_ids":["https://openalex.org/I83019370"]},{"raw_affiliation_string":"Eindhoven University of Technology, Eindhoven, The Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080242338","display_name":"Uzay Kaymak","orcid":"https://orcid.org/0000-0002-4500-9098"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Uzay Kaymak","raw_affiliation_strings":["Eindhoven University of Technology,Eindhoven,The Netherlands","Eindhoven University of Technology, Eindhoven, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology,Eindhoven,The Netherlands","institution_ids":["https://openalex.org/I83019370"]},{"raw_affiliation_string":"Eindhoven University of Technology, Eindhoven, The Netherlands","institution_ids":["https://openalex.org/I83019370"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I83019370"],"apc_list":null,"apc_paid":null,"fwci":0.8642,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.74940431,"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":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11182","display_name":"Auction Theory and Applications","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T11182","display_name":"Auction Theory and Applications","score":0.9997000098228455,"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/T11161","display_name":"Consumer Market Behavior and Pricing","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/1406","display_name":"Marketing"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9951000213623047,"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/bidding","display_name":"Bidding","score":0.7858216762542725},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7803006172180176},{"id":"https://openalex.org/keywords/common-value-auction","display_name":"Common value auction","score":0.719257116317749},{"id":"https://openalex.org/keywords/revenue","display_name":"Revenue","score":0.6328633427619934},{"id":"https://openalex.org/keywords/real-time-bidding","display_name":"Real-time bidding","score":0.5582684278488159},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5548386573791504},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4459395110607147},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4440199136734009},{"id":"https://openalex.org/keywords/microeconomics","display_name":"Microeconomics","score":0.42783790826797485},{"id":"https://openalex.org/keywords/operations-research","display_name":"Operations research","score":0.3266918957233429},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2688041925430298},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.2659076452255249},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.18221837282180786},{"id":"https://openalex.org/keywords/finance","display_name":"Finance","score":0.09101104736328125},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0858946144580841}],"concepts":[{"id":"https://openalex.org/C9233905","wikidata":"https://www.wikidata.org/wiki/Q3276328","display_name":"Bidding","level":2,"score":0.7858216762542725},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7803006172180176},{"id":"https://openalex.org/C163239763","wikidata":"https://www.wikidata.org/wiki/Q5153637","display_name":"Common value auction","level":2,"score":0.719257116317749},{"id":"https://openalex.org/C195487862","wikidata":"https://www.wikidata.org/wiki/Q850210","display_name":"Revenue","level":2,"score":0.6328633427619934},{"id":"https://openalex.org/C1525070","wikidata":"https://www.wikidata.org/wiki/Q2134714","display_name":"Real-time bidding","level":3,"score":0.5582684278488159},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5548386573791504},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4459395110607147},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4440199136734009},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.42783790826797485},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.3266918957233429},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2688041925430298},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.2659076452255249},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.18221837282180786},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.09101104736328125},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0858946144580841},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9533817","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533817","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.tue.nl:openaire/a821ddcb-9b28-446f-acb7-21113aaee706","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/a821ddcb-9b28-446f-acb7-21113aaee706","pdf_url":"https://pure.tue.nl/ws/files/172689328/ijcnn_camera_ready.pdf","source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Refaei Afshar, R, Rhuggenaath, J, Zhang, Y & Kaymak, U 2021, A Reward Shaping Approach for Reserve Price Optimization using Deep Reinforcement Learning. in 2021 International Joint Conference on Neural Networks (IJCNN)., 9533817, Institute of Electrical and Electronics Engineers, 2021 International Joint Conference on Neural Networks, IJCNN 2021, Shenzhen, China, 18/07/21. https://doi.org/10.1109/IJCNN52387.2021.9533817","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:pure.tue.nl:publications/a821ddcb-9b28-446f-acb7-21113aaee706","is_oa":true,"landing_page_url":"http://www.scopus.com/inward/record.url?scp=85116412853&partnerID=8YFLogxK","pdf_url":null,"source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Refaei Afshar, R, Rhuggenaath, J, Zhang, Y & Kaymak, U 2021, A Reward Shaping Approach for Reserve Price Optimization using Deep Reinforcement Learning. in 2021 International Joint Conference on Neural Networks (IJCNN)., 9533817, Institute of Electrical and Electronics Engineers, 2021 International Joint Conference on Neural Networks, IJCNN 2021, Shenzhen, China, 18/07/21. https://doi.org/10.1109/IJCNN52387.2021.9533817","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:tue:oai:pure.tue.nl:publications/a821ddcb-9b28-446f-acb7-21113aaee706","is_oa":true,"landing_page_url":"https://research.tue.nl/nl/publications/a821ddcb-9b28-446f-acb7-21113aaee706","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"info:eu-repo/semantics/conferencepaper"}],"best_oa_location":{"id":"pmh:oai:pure.tue.nl:openaire/a821ddcb-9b28-446f-acb7-21113aaee706","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/a821ddcb-9b28-446f-acb7-21113aaee706","pdf_url":"https://pure.tue.nl/ws/files/172689328/ijcnn_camera_ready.pdf","source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Refaei Afshar, R, Rhuggenaath, J, Zhang, Y & Kaymak, U 2021, A Reward Shaping Approach for Reserve Price Optimization using Deep Reinforcement Learning. in 2021 International Joint Conference on Neural Networks (IJCNN)., 9533817, Institute of Electrical and Electronics Engineers, 2021 International Joint Conference on Neural Networks, IJCNN 2021, Shenzhen, China, 18/07/21. https://doi.org/10.1109/IJCNN52387.2021.9533817","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.4300000071525574}],"awards":[],"funders":[{"id":"https://openalex.org/F4320338388","display_name":"Eurostars","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3167696941.pdf","grobid_xml":"https://content.openalex.org/works/W3167696941.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1757796397","https://openalex.org/W1777239053","https://openalex.org/W1982239148","https://openalex.org/W2069696398","https://openalex.org/W2077055010","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2317606158","https://openalex.org/W2530299800","https://openalex.org/W2736601468","https://openalex.org/W2774987586","https://openalex.org/W2775463748","https://openalex.org/W2788125442","https://openalex.org/W2804073446","https://openalex.org/W2892046593","https://openalex.org/W2902922568","https://openalex.org/W2912063360","https://openalex.org/W2921600809","https://openalex.org/W2951002685","https://openalex.org/W2952511194","https://openalex.org/W2952536678","https://openalex.org/W2963252944","https://openalex.org/W2963841569","https://openalex.org/W2964043796","https://openalex.org/W2974685809","https://openalex.org/W2980960050","https://openalex.org/W2998596932","https://openalex.org/W3006439062","https://openalex.org/W3047974796","https://openalex.org/W3082514436","https://openalex.org/W3099724660","https://openalex.org/W3103752844","https://openalex.org/W3104945556","https://openalex.org/W3123573640","https://openalex.org/W4214717370","https://openalex.org/W4249889562","https://openalex.org/W4298857966","https://openalex.org/W6638088447","https://openalex.org/W6692846177","https://openalex.org/W6785742451"],"related_works":["https://openalex.org/W2990183840","https://openalex.org/W2758970837","https://openalex.org/W3016027016","https://openalex.org/W3122350565","https://openalex.org/W1553934122","https://openalex.org/W2386843674","https://openalex.org/W1599761937","https://openalex.org/W2073502489","https://openalex.org/W2145949676","https://openalex.org/W3122094806"],"abstract_inverted_index":{"Real":[0,16],"Time":[1],"Bidding":[2],"is":[3,55,120,179],"the":[4,59,79,93,111,114,125,134,140,156,173,211],"process":[5],"of":[6,61,96,166,176,195,201,207],"selling":[7],"and":[8,39,73,172],"buying":[9],"online":[10],"advertisements":[11],"in":[12,21,205],"real":[13],"time":[14,17],"auctions.":[15],"auctions":[18,38],"are":[19],"performed":[20],"header":[22,62],"bidding":[23,63],"partners":[24],"or":[25,50],"ad":[26,31,48,66,103],"exchanges":[27,34,104],"to":[28,138,150],"sell":[29],"publishers'":[30],"placements.":[32],"Ad":[33],"run":[35],"second":[36],"price":[37,42,54,95,168],"a":[40,86,145,182,186,193],"reserve":[41,53,71,94,167],"should":[43],"be":[44],"set":[45,194],"for":[46,91,123,155],"each":[47,177],"placement":[49],"impression.":[51],"This":[52,117],"normally":[56],"determined":[57],"by":[58],"bids":[60],"partners.":[64],"However,":[65],"exchange":[67],"may":[68],"outbid":[69],"higher":[70],"prices":[72],"optimizing":[74],"this":[75,82,162],"value":[76,175],"largely":[77],"affects":[78],"revenue.":[80,135],"In":[81,136],"paper,":[83],"we":[84,143,188],"propose":[85],"deep":[87],"reinforcement":[88,157],"learning":[89,158],"approach":[90,149],"adjusting":[92],"individual":[97],"impressions":[98],"using":[99],"contextual":[100],"information.":[101],"Normally,":[102],"do":[105],"not":[106,121],"return":[107],"any":[108],"information":[109,132],"about":[110,133],"auction":[112],"except":[113],"sold-unsold":[115],"status.":[116],"binary":[118],"feedback":[119],"suitable":[122],"maximizing":[124],"revenue":[126,208],"because":[127],"it":[128],"contains":[129],"no":[130],"explicit":[131],"order":[137],"enrich":[139],"reward":[141,147,153,174],"function,":[142],"develop":[144],"novel":[146],"shaping":[148],"provide":[151],"informative":[152],"signal":[154],"agent.":[159],"Based":[160],"on":[161,192],"approach,":[163],"different":[164,170],"intervals":[165],"get":[169],"weights":[171],"interval":[178],"learned":[180],"through":[181],"search":[183],"procedure.":[184],"Using":[185],"simulator,":[187],"test":[189],"our":[190,202],"method":[191,204],"impressions.":[196],"Results":[197],"show":[198],"superior":[199],"performance":[200],"proposed":[203],"terms":[206],"compared":[209],"with":[210],"baselines.":[212]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2021-06-22T00:00:00"}