{"id":"https://openalex.org/W3167326770","doi":"https://doi.org/10.24963/ijcai.2021/75","title":"Addressing the Long-term Impact of ML Decisions via Policy Regret","display_name":"Addressing the Long-term Impact of ML Decisions via Policy Regret","publication_year":2021,"publication_date":"2021-08-01","ids":{"openalex":"https://openalex.org/W3167326770","doi":"https://doi.org/10.24963/ijcai.2021/75","mag":"3167326770"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2021/75","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/75","pdf_url":"https://www.ijcai.org/proceedings/2021/0075.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth 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/2021/0075.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059597480","display_name":"David Lindner","orcid":"https://orcid.org/0000-0001-7051-7433"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"David Lindner","raw_affiliation_strings":["ETH Zurich","ETH Z\u00fcrich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"ETH Z\u00fcrich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037735812","display_name":"Hoda Heidari","orcid":"https://orcid.org/0000-0003-3710-4076"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hoda Heidari","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003040843","display_name":"Andreas Krause","orcid":"https://orcid.org/0000-0001-7260-9673"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Andreas Krause","raw_affiliation_strings":["ETH Zurich","ETH Z\u00fcrich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"ETH Z\u00fcrich","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5059597480"],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08121351,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"537","last_page":"544"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":1.0,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":1.0,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9911999702453613,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9909999966621399,"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/regret","display_name":"Regret","score":0.9860415458679199},{"id":"https://openalex.org/keywords/decision-maker","display_name":"Decision maker","score":0.6532534956932068},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.6270084381103516},{"id":"https://openalex.org/keywords/time-horizon","display_name":"Time horizon","score":0.5655171275138855},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5544490218162537},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.550287127494812},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.4507656991481781},{"id":"https://openalex.org/keywords/operations-research","display_name":"Operations research","score":0.43680667877197266},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4312695562839508},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.3868776857852936},{"id":"https://openalex.org/keywords/management-science","display_name":"Management science","score":0.20407256484031677},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1490618884563446},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12844857573509216},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09178468585014343},{"id":"https://openalex.org/keywords/finance","display_name":"Finance","score":0.08228117227554321}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.9860415458679199},{"id":"https://openalex.org/C2986080485","wikidata":"https://www.wikidata.org/wiki/Q1331926","display_name":"Decision maker","level":2,"score":0.6532534956932068},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.6270084381103516},{"id":"https://openalex.org/C28761237","wikidata":"https://www.wikidata.org/wiki/Q7805321","display_name":"Time horizon","level":2,"score":0.5655171275138855},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5544490218162537},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.550287127494812},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.4507656991481781},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.43680667877197266},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4312695562839508},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.3868776857852936},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.20407256484031677},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1490618884563446},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12844857573509216},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09178468585014343},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.08228117227554321},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.24963/ijcai.2021/75","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/75","pdf_url":"https://www.ijcai.org/proceedings/2021/0075.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2106.01325","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.01325","pdf_url":"https://arxiv.org/pdf/2106.01325","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":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2106.01325","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2106.01325","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"},{"id":"mag:3167326770","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"doi:10.24963/ijcai.2021/75","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/75","pdf_url":"https://www.ijcai.org/proceedings/2021/0075.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4000000059604645,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G2424045644","display_name":null,"funder_award_id":"IIS2040929","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/F4320321652","display_name":"Eidgen\u00f6ssische Technische Hochschule Z\u00fcrich","ror":"https://ror.org/05a28rw58"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3167326770.pdf","grobid_xml":"https://content.openalex.org/works/W3167326770.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W157259654","https://openalex.org/W656309451","https://openalex.org/W1577069963","https://openalex.org/W1998111611","https://openalex.org/W1998498767","https://openalex.org/W2049934117","https://openalex.org/W2056921512","https://openalex.org/W2077902449","https://openalex.org/W2100960835","https://openalex.org/W2101379030","https://openalex.org/W2147398813","https://openalex.org/W2530395818","https://openalex.org/W2540757487","https://openalex.org/W2576746119","https://openalex.org/W2765564115","https://openalex.org/W2773444500","https://openalex.org/W2788481061","https://openalex.org/W2888023058","https://openalex.org/W2888078780","https://openalex.org/W2888421747","https://openalex.org/W2889169527","https://openalex.org/W2891425177","https://openalex.org/W2904609718","https://openalex.org/W2920646515","https://openalex.org/W2953001331","https://openalex.org/W2962753953","https://openalex.org/W2962771056","https://openalex.org/W2962821829","https://openalex.org/W2962922665","https://openalex.org/W2963032716","https://openalex.org/W2963771282","https://openalex.org/W3001765450","https://openalex.org/W3002654242","https://openalex.org/W3046373002","https://openalex.org/W3102381603","https://openalex.org/W3106000504","https://openalex.org/W3121201812","https://openalex.org/W3124980499","https://openalex.org/W3126362025"],"related_works":["https://openalex.org/W2145964516","https://openalex.org/W2906261151","https://openalex.org/W2164831377","https://openalex.org/W2750652610","https://openalex.org/W2234795139","https://openalex.org/W2994548416","https://openalex.org/W3105659172","https://openalex.org/W2019862182","https://openalex.org/W3144388317","https://openalex.org/W3006115515","https://openalex.org/W3006822506","https://openalex.org/W1966635311","https://openalex.org/W2889310599","https://openalex.org/W3214277921","https://openalex.org/W2998638191","https://openalex.org/W2531869355","https://openalex.org/W2615680919","https://openalex.org/W2146198175","https://openalex.org/W3143674903","https://openalex.org/W1536350240"],"abstract_inverted_index":{"Machine":[0],"Learning":[1],"(ML)":[2],"increasingly":[3],"informs":[4],"the":[5,60,73,81,96,133,143],"allocation":[6,65,116],"of":[7,63,98,117,135],"opportunities":[8,118],"to":[9,45],"individuals":[10],"and":[11,20,30,147,169],"communities":[12,55],"in":[13,32,47,71,95,176],"areas":[14],"such":[15],"as":[16,56],"lending,":[17],"education,":[18],"employment,":[19],"beyond.":[21],"Such":[22],"decisions":[23],"often":[24],"impact":[25],"their":[26],"subjects'":[27],"future":[28],"characteristics":[29],"capabilities":[31],"an":[33,113,121,149],"a":[34,69,107,138],"priori":[35],"unknown":[36],"fashion.":[37],"The":[38],"decision-maker,":[39],"therefore,":[40],"faces":[41],"exploration-exploitation":[42],"dilemmas":[43],"akin":[44],"those":[46],"multi-armed":[48],"bandits.":[49],"Following":[50],"prior":[51],"work,":[52],"we":[53,67],"model":[54],"arms.":[57],"To":[58],"capture":[59,129],"long-term":[61],"effects":[62],"ML-based":[64],"decisions,":[66],"study":[68],"setting":[70],"which":[72],"reward":[74,89],"from":[75],"each":[76],"arm":[77],"evolves":[78],"every":[79],"time":[80,159,180],"decision-maker":[82],"pulls":[83,99],"that":[84,91,112,171],"arm.":[85],"We":[86,110,128,161],"focus":[87],"on":[88],"functions":[90],"are":[92],"initially":[93],"increasing":[94],"number":[97],"but":[100],"may":[101],"become":[102],"(and":[103],"remain)":[104],"decreasing":[105],"after":[106],"certain":[108],"point.":[109],"argue":[111],"acceptable":[114],"sequential":[115],"must":[119],"take":[120],"arm's":[122],"potential":[123],"for":[124,156,178],"growth":[125],"into":[126],"account.":[127],"these":[130],"considerations":[131],"through":[132],"notion":[134,141],"policy":[136,154],"regret,":[137,146],"much":[139],"stronger":[140],"than":[142],"often-studied":[144],"external":[145],"present":[148],"algorithm":[150,165],"with":[151,166],"provably":[152],"sub-linear":[153],"regret":[155],"sufficiently":[157],"long":[158,179],"horizons.":[160,181],"empirically":[162],"compare":[163],"our":[164],"several":[167],"baselines":[168],"find":[170],"it":[172],"consistently":[173],"outperforms":[174],"them,":[175],"particular":[177]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}