{"id":"https://openalex.org/W3013297014","doi":"https://doi.org/10.5555/3398761.3398911","title":"Strategyproof Reinforcement Learning for Online Resource Allocation","display_name":"Strategyproof Reinforcement Learning for Online Resource Allocation","publication_year":2020,"publication_date":"2020-05-05","ids":{"openalex":"https://openalex.org/W3013297014","doi":"https://doi.org/10.5555/3398761.3398911","mag":"3013297014"},"language":"en","primary_location":{"id":"pmh:oai:eprints.soton.ac.uk:438382","is_oa":true,"landing_page_url":null,"pdf_url":"https://eprints.soton.ac.uk/438382/1/srl_aamas_main.pdf","source":{"id":"https://openalex.org/S4306401019","display_name":"ePrints Soton (University of Southampton)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I43439940","host_organization_name":"University of Southampton","host_organization_lineage":["https://openalex.org/I43439940"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"},"type":"conference-paper","indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.soton.ac.uk/438382/1/srl_aamas_main.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011370879","display_name":"Sebastian Stein","orcid":"https://orcid.org/0000-0003-2858-8857"},"institutions":[{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sebastian Stein","raw_affiliation_strings":["Univ of Southampton, Southampton, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-2858-8857","affiliations":[{"raw_affiliation_string":"Univ of Southampton, Southampton, United Kingdom","institution_ids":["https://openalex.org/I43439940"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058854740","display_name":"Mateusz Ochal","orcid":"https://orcid.org/0000-0003-3799-5921"},"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":"Mateusz Ochal","raw_affiliation_strings":["University of Edinburgh, Edinburgh, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-3799-5921","affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046277911","display_name":"Ioana-Adriana Moisoiu","orcid":null},"institutions":[{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ioana-Adriana Moisoiu","raw_affiliation_strings":["Univ of Southampton, Southampton, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ of Southampton, Southampton, United Kingdom","institution_ids":["https://openalex.org/I43439940"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040869025","display_name":"Enrico Gerding","orcid":"https://orcid.org/0000-0001-7200-552X"},"institutions":[{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Enrico Gerding","raw_affiliation_strings":["Univ of Southampton, Southampton, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ of Southampton, Southampton, United Kingdom","institution_ids":["https://openalex.org/I43439940"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011324325","display_name":"Raghu Ganti","orcid":"https://orcid.org/0000-0003-3658-7918"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raghu Ganti","raw_affiliation_strings":["IBM Research , Yorktown Heights, NY , USA"],"raw_orcid":"https://orcid.org/0000-0003-3658-7918","affiliations":[{"raw_affiliation_string":"IBM Research , Yorktown Heights, NY , USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088400668","display_name":"Ting He","orcid":"https://orcid.org/0000-0003-1070-7483"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ting He","raw_affiliation_strings":["Penn State University, State College, PA, USA"],"raw_orcid":"https://orcid.org/0000-0003-1070-7483","affiliations":[{"raw_affiliation_string":"Penn State University, State College, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103832183","display_name":"Tom La Porta","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tom La Porta","raw_affiliation_strings":["Penn State University, State College, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Penn State University, State College, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1296","last_page":"1304"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11182","display_name":"Auction Theory and Applications","score":0.9995999932289124,"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":0.9995999932289124,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T10270","display_name":"Blockchain Technology Applications and Security","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.9232995510101318},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7460410594940186},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7228003144264221},{"id":"https://openalex.org/keywords/mechanism-design","display_name":"Mechanism design","score":0.6295092701911926},{"id":"https://openalex.org/keywords/resource-allocation","display_name":"Resource allocation","score":0.6092914938926697},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5241339802742004},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.48905596137046814},{"id":"https://openalex.org/keywords/social-welfare","display_name":"Social Welfare","score":0.47255250811576843},{"id":"https://openalex.org/keywords/resource-management","display_name":"Resource management (computing)","score":0.47070977091789246},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4699559211730957},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4411994218826294},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39179107546806335},{"id":"https://openalex.org/keywords/operations-research","display_name":"Operations research","score":0.3459351658821106},{"id":"https://openalex.org/keywords/microeconomics","display_name":"Microeconomics","score":0.28064873814582825},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.16186341643333435},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.12412482500076294},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.08857592940330505},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0831446647644043}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9232995510101318},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7460410594940186},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7228003144264221},{"id":"https://openalex.org/C153517567","wikidata":"https://www.wikidata.org/wiki/Q26090","display_name":"Mechanism design","level":2,"score":0.6295092701911926},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.6092914938926697},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5241339802742004},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.48905596137046814},{"id":"https://openalex.org/C536738050","wikidata":"https://www.wikidata.org/wiki/Q3249071","display_name":"Social Welfare","level":2,"score":0.47255250811576843},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.47070977091789246},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4699559211730957},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4411994218826294},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39179107546806335},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.3459351658821106},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.28064873814582825},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.16186341643333435},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.12412482500076294},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.08857592940330505},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0831446647644043},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:eprints.soton.ac.uk:438382","is_oa":true,"landing_page_url":null,"pdf_url":"https://eprints.soton.ac.uk/438382/1/srl_aamas_main.pdf","source":{"id":"https://openalex.org/S4306401019","display_name":"ePrints Soton (University of Southampton)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I43439940","host_organization_name":"University of Southampton","host_organization_lineage":["https://openalex.org/I43439940"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"},{"id":"mag:3013297014","is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/conf/atal/aamas2020.html#0001OMGG0P20","pdf_url":null,"source":{"id":"https://openalex.org/S4306417597","display_name":"Adaptive Agents and Multi-Agents Systems","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":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"Adaptive Agents and Multi-Agents Systems","raw_type":null}],"best_oa_location":{"id":"pmh:oai:eprints.soton.ac.uk:438382","is_oa":true,"landing_page_url":null,"pdf_url":"https://eprints.soton.ac.uk/438382/1/srl_aamas_main.pdf","source":{"id":"https://openalex.org/S4306401019","display_name":"ePrints Soton (University of Southampton)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I43439940","host_organization_name":"University of Southampton","host_organization_lineage":["https://openalex.org/I43439940"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G3056544016","display_name":null,"funder_award_id":"W911NF-16-3-0001","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"},{"id":"https://openalex.org/G5259331294","display_name":null,"funder_award_id":"W911NF","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"}],"funders":[{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3013297014.pdf","grobid_xml":"https://content.openalex.org/works/W3013297014.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W2001344406","https://openalex.org/W2051290144","https://openalex.org/W2109516767","https://openalex.org/W2111957769","https://openalex.org/W2131101582","https://openalex.org/W2135682453","https://openalex.org/W2145339207","https://openalex.org/W2150582214","https://openalex.org/W2165436315","https://openalex.org/W2394678422","https://openalex.org/W2546571074","https://openalex.org/W2617364249","https://openalex.org/W2624989916","https://openalex.org/W2751904527","https://openalex.org/W2784711283","https://openalex.org/W2793855276","https://openalex.org/W2796447772","https://openalex.org/W2905057216","https://openalex.org/W2905685817","https://openalex.org/W2949710576","https://openalex.org/W2956517125","https://openalex.org/W2963440040","https://openalex.org/W3139377883"],"related_works":["https://openalex.org/W2911593283","https://openalex.org/W2118973744","https://openalex.org/W3169967185","https://openalex.org/W2072872196","https://openalex.org/W2592180803","https://openalex.org/W3100039483","https://openalex.org/W2935449623","https://openalex.org/W2141086070","https://openalex.org/W2952358274","https://openalex.org/W3092438371","https://openalex.org/W2964384607","https://openalex.org/W2376806823","https://openalex.org/W2182779842","https://openalex.org/W21950330","https://openalex.org/W2991428952","https://openalex.org/W2620712696","https://openalex.org/W3122172330","https://openalex.org/W3109663121","https://openalex.org/W2928798670","https://openalex.org/W2891764518"],"abstract_inverted_index":{"We":[0],"consider":[1],"an":[2],"online":[3],"resource":[4,14],"allocation":[5],"problem":[6],"where":[7],"tasks":[8],"with":[9],"specific":[10,127],"values,":[11],"sizes":[12],"and":[13,20,69,86,92],"requirements":[15,52],"arrive":[16],"dynamically":[17],"over":[18],"time,":[19],"have":[21],"to":[22,59,80,124],"be":[23],"either":[24],"serviced":[25],"or":[26,53],"rejected":[27],"immediately.":[28],"Reinforcement":[29],"learning":[30,42,77],"is":[31,58,84],"a":[32,71],"promising":[33],"approach":[34],"for":[35],"this,":[36,64],"but":[37],"existing":[38],"work":[39],"on":[40,75],"reinforcement":[41,76],"has":[43],"neglected":[44],"that":[45,78,100,105,118],"task":[46,51],"owners":[47],"may":[48],"misreport":[49],"their":[50,60],"values":[54],"strategically":[55],"when":[56],"this":[57],"benefit.":[61],"To":[62],"address":[63],"we":[65,98],"apply":[66],"mechanism":[67,73],"design":[68],"propose":[70],"novel":[72],"based":[74],"aims":[79],"maximise":[81],"social":[82,113],"welfare,":[83,114],"strategyproof":[85],"individually":[87],"rational":[88],"(i.e.,":[89],"truthful":[90],"reporting":[91],"participation":[93],"are":[94,106],"incentivised).":[95],"In":[96],"experiments,":[97],"show":[99],"our":[101],"algorithm":[102],"achieves":[103],"results":[104],"typically":[107],"within":[108],"90%":[109],"of":[110],"the":[111],"optimal":[112],"while":[115],"outperforming":[116],"approaches":[117],"use":[119],"fixed":[120],"pricing":[121],"(by":[122],"up":[123],"86%":[125],"in":[126],"cases).":[128]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
