{"id":"https://openalex.org/W4406610289","doi":"https://doi.org/10.1109/tac.2025.3532181","title":"Model Approximation in MDPs With Unbounded Per-Step Cost","display_name":"Model Approximation in MDPs With Unbounded Per-Step Cost","publication_year":2025,"publication_date":"2025-01-20","ids":{"openalex":"https://openalex.org/W4406610289","doi":"https://doi.org/10.1109/tac.2025.3532181"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2025.3532181","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2025.3532181","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automatic Control","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086071736","display_name":"Berk Bozkurt","orcid":"https://orcid.org/0000-0002-5282-5843"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Berk Bozkurt","raw_affiliation_strings":["Department of Electrical and Computer Engineering, McGill University, Montreal, QC, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, McGill University, Montreal, QC, Canada","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005770424","display_name":"Aditya Mahajan","orcid":"https://orcid.org/0000-0001-8125-1191"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Aditya Mahajan","raw_affiliation_strings":["Department of Electrical and Computer Engineering, McGill University, Montreal, QC, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, McGill University, Montreal, QC, Canada","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040616226","display_name":"Ashutosh Nayyar","orcid":"https://orcid.org/0000-0001-8310-7505"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashutosh Nayyar","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100627878","display_name":"Yi Ouyang","orcid":"https://orcid.org/0000-0003-0556-4393"},"institutions":[{"id":"https://openalex.org/I16269868","display_name":"Santa Clara University","ror":"https://ror.org/03ypqe447","country_code":"US","type":"education","lineage":["https://openalex.org/I16269868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Ouyang","raw_affiliation_strings":["Atmanity, Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"Atmanity, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I16269868"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5086071736"],"corresponding_institution_ids":["https://openalex.org/I5023651"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00964691,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"70","issue":"7","first_page":"4624","last_page":"4639"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9911999702453613,"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":0.9911999702453613,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9865000247955322,"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/T12288","display_name":"Optimization and Search Problems","score":0.982200026512146,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/computer-science","display_name":"Computer science","score":0.5295884013175964},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4697965383529663},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3575955629348755},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.34509968757629395}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5295884013175964},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4697965383529663},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3575955629348755},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.34509968757629395}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tac.2025.3532181","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2025.3532181","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automatic Control","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G218463587","display_name":null,"funder_award_id":"CFPMN2-30","funder_id":"https://openalex.org/F124502447","funder_display_name":"Innovation for Defence Excellence and Security"},{"id":"https://openalex.org/G5065949317","display_name":null,"funder_award_id":"RGPIN-2021-03511","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F124502447","display_name":"Innovation for Defence Excellence and Security","ror":null},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1578233523","https://openalex.org/W1895076743","https://openalex.org/W1966807936","https://openalex.org/W1974469893","https://openalex.org/W1995688924","https://openalex.org/W2009543467","https://openalex.org/W2015114013","https://openalex.org/W2017419329","https://openalex.org/W2024437990","https://openalex.org/W2035954066","https://openalex.org/W2046637502","https://openalex.org/W2057241181","https://openalex.org/W2098432798","https://openalex.org/W2114091196","https://openalex.org/W2127576890","https://openalex.org/W2145778650","https://openalex.org/W2146290970","https://openalex.org/W2149148771","https://openalex.org/W2316506176","https://openalex.org/W2963272571","https://openalex.org/W2963619045","https://openalex.org/W2964034900","https://openalex.org/W2964241534","https://openalex.org/W2998102890","https://openalex.org/W3008165446","https://openalex.org/W3020371095","https://openalex.org/W3039633551","https://openalex.org/W4205537960","https://openalex.org/W4233762729","https://openalex.org/W4236942139","https://openalex.org/W4249345565","https://openalex.org/W4253201987","https://openalex.org/W4253349640","https://openalex.org/W4287637954","https://openalex.org/W4287640641","https://openalex.org/W4391021135","https://openalex.org/W6635516443","https://openalex.org/W6684909995","https://openalex.org/W6719911377","https://openalex.org/W6763088550","https://openalex.org/W6784034564","https://openalex.org/W6784311389"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4391375266","https://openalex.org/W1979597421","https://openalex.org/W2007980826","https://openalex.org/W2061531152","https://openalex.org/W3002753104","https://openalex.org/W2077600819","https://openalex.org/W2142036596","https://openalex.org/W2072657027"],"abstract_inverted_index":{"In":[0],"this":[1,69],"article,":[2],"we":[3,26],"consider":[4],"the":[5,52,59,77,80,98,124,136,149],"problem":[6],"of":[7,51,76,83,102,123,148],"designing":[8],"a":[9,73],"control":[10],"policy":[11,44],"for":[12],"an":[13,31,42],"infinite-horizon":[14],"discounted":[15],"cost":[16,140],"Markov":[17],"decision":[18],"process":[19],"<inline-formula":[20,34,45,62,84,92,103],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[21,35,46,63,85,93,104],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[22,36,47,64,86,94,105],"notation=\"LaTeX\">$\\mathcal":[23,65,95,106],"{M}$</tex-math></inline-formula>":[24,96],"when":[25,56,89],"only":[27],"have":[28],"access":[29],"to":[30,157],"approximate":[32,53,152],"model":[33,54,61],"notation=\"LaTeX\">$\\hat{\\mathcal":[37],"{M}}$</tex-math></inline-formula>.":[38],"How":[39],"well":[40],"does":[41],"optimal":[43,99],"notation=\"LaTeX\">$\\hat{\\pi":[48,87],"}^{\\star":[49],"}$</tex-math></inline-formula>":[50],"perform":[55],"used":[57,90],"in":[58,91],"original":[60,150],"{M}$</tex-math></inline-formula>?":[66],"We":[67,108,127,154],"answer":[68],"question":[70],"by":[71,119],"bounding":[72],"weighted":[74,137,143],"norm":[75],"difference":[78],"between":[79,139,145],"value":[81,100],"function":[82,101],"}^\\star$</tex-math></inline-formula>":[88],"and":[97,113,142,151],"{M}$</tex-math></inline-formula>.":[107],"then":[109],"extend":[110],"our":[111,159],"results":[112],"obtain":[114],"potentially":[115],"tighter":[116],"upper":[117,130],"bounds":[118,131],"considering":[120],"affine":[121],"transformations":[122],"per-step":[125],"cost.":[126],"further":[128],"provide":[129],"that":[132],"explicitly":[133],"depend":[134],"on":[135],"distance":[138,144],"functions":[141],"transition":[146],"kernels":[147],"models.":[153],"present":[155],"examples":[156],"illustrate":[158],"results.":[160]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}