{"id":"https://openalex.org/W4391021135","doi":"https://doi.org/10.1109/cdc49753.2023.10383590","title":"Weighted-Norm Bounds on Model Approximation in MDPs with Unbounded Per-Step Cost","display_name":"Weighted-Norm Bounds on Model Approximation in MDPs with Unbounded Per-Step Cost","publication_year":2023,"publication_date":"2023-12-13","ids":{"openalex":"https://openalex.org/W4391021135","doi":"https://doi.org/10.1109/cdc49753.2023.10383590"},"language":"en","primary_location":{"id":"doi:10.1109/cdc49753.2023.10383590","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cdc49753.2023.10383590","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 62nd IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.82308/26254","any_repository_has_fulltext":null},"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":["McGill University,Department of Electrical and Computer Engineering,Montreal,QC,Canada","Department of Electrical and Computer Engineering, McGill University, Montreal, QC, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"McGill University,Department of Electrical and Computer Engineering,Montreal,QC,Canada","institution_ids":["https://openalex.org/I5023651"]},{"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":["McGill University,Department of Electrical and Computer Engineering,Montreal,QC,Canada","Department of Electrical and Computer Engineering, McGill University, Montreal, QC, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"McGill University,Department of Electrical and Computer Engineering,Montreal,QC,Canada","institution_ids":["https://openalex.org/I5023651"]},{"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":["University of Southern California,Department of Electrical and Computer Engineering,Los Angeles,CA,USA","Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Department of Electrical and Computer Engineering,Los Angeles,CA,USA","institution_ids":["https://openalex.org/I1174212"]},{"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/I4210166566","display_name":"Preferred Networks (Japan)","ror":"https://ror.org/05xeefy56","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210166566"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yi Ouyang","raw_affiliation_strings":["Preferred Networks America,Burlingame,CA,USA","Preferred Networks America, Burlingame, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Preferred Networks America,Burlingame,CA,USA","institution_ids":["https://openalex.org/I4210166566"]},{"raw_affiliation_string":"Preferred Networks America, Burlingame, CA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":3,"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":0.3317,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67703535,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"23","issue":null,"first_page":"7817","last_page":"7823"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9861000180244446,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9861000180244446,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9739999771118164,"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/T12288","display_name":"Optimization and Search Problems","score":0.9603000283241272,"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/bounding-overwatch","display_name":"Bounding overwatch","score":0.5633575320243835},{"id":"https://openalex.org/keywords/norm","display_name":"Norm (philosophy)","score":0.5251390933990479},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.49866414070129395},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4581148028373718},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.40555012226104736},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.3980238735675812},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.36798352003097534},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3511736989021301},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2934560775756836},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.07915762066841125}],"concepts":[{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.5633575320243835},{"id":"https://openalex.org/C191795146","wikidata":"https://www.wikidata.org/wiki/Q3878446","display_name":"Norm (philosophy)","level":2,"score":0.5251390933990479},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.49866414070129395},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4581148028373718},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.40555012226104736},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.3980238735675812},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.36798352003097534},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3511736989021301},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2934560775756836},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.07915762066841125},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/cdc49753.2023.10383590","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cdc49753.2023.10383590","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 62nd IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},{"id":"pmh:oai:escholarship.mcgill.ca:wd3763272","is_oa":false,"landing_page_url":"https://escholarship.mcgill.ca/concern/theses/wd3763272","pdf_url":null,"source":{"id":"https://openalex.org/S4306401568","display_name":"eScholarship@McGill (McGill)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I5023651","host_organization_name":"McGill University","host_organization_lineage":["https://openalex.org/I5023651"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Thesis"},{"id":"doi:10.82308/26254","is_oa":true,"landing_page_url":"https://doi.org/10.82308/26254","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"thesis"}],"best_oa_location":{"id":"doi:10.82308/26254","is_oa":true,"landing_page_url":"https://doi.org/10.82308/26254","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"thesis"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6169346761","display_name":null,"funder_award_id":"ECCS 2025732,ECCS 1750041","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1591992921","https://openalex.org/W1966807936","https://openalex.org/W1995688924","https://openalex.org/W2009543467","https://openalex.org/W2010654234","https://openalex.org/W2015114013","https://openalex.org/W2017419329","https://openalex.org/W2024437990","https://openalex.org/W2035954066","https://openalex.org/W2046637502","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/W2170296074","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/W4210545817","https://openalex.org/W4249345565","https://openalex.org/W4253349640","https://openalex.org/W4287637954","https://openalex.org/W4287863878","https://openalex.org/W4311128572","https://openalex.org/W4391021135","https://openalex.org/W6635516443","https://openalex.org/W6674995601","https://openalex.org/W6684909995","https://openalex.org/W6719911377","https://openalex.org/W6763088550","https://openalex.org/W6784311389"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W3166204570","https://openalex.org/W3121246613","https://openalex.org/W2132137594","https://openalex.org/W2093537624","https://openalex.org/W350499458","https://openalex.org/W2062170304","https://openalex.org/W4231562521","https://openalex.org/W2980963558","https://openalex.org/W4240240174"],"abstract_inverted_index":{"We":[0,61,143],"consider":[1],"the":[2,43,54,74,77,91,115,128,137,162],"problem":[3,160],"of":[4,73,80,95,101,127,139],"designing":[5],"a":[6,70,152],"control":[7,159],"policy":[8,38],"for":[9,42,110,147,156],"an":[10,27,36,63,157],"infinite-horizon":[11],"discounted":[12,163],"cost":[13,117],"Markov":[14],"Decision":[15],"Process":[16],"(MDP)":[17],"<tex":[18,30,39,57,81,87,96],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[19,31,40,58,82,88,97],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\mathcal{M}$</tex>":[20,59,89],"when":[21,51,84,114],"we":[22,34],"only":[23,135],"have":[24],"access":[25],"to":[26,65,106,125],"approximate":[28,44],"model":[29,56,155],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\hat{\\mathcal{M}}$</tex>.":[32],"If":[33],"design":[35],"optimal":[37,92],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\hat{\\pi}^{\\star}$</tex>":[41,83],"model,":[45],"how":[46],"well":[47],"does":[48],"it":[49],"perform":[50],"used":[52,85],"in":[53,86,123],"true":[55],"?":[60],"provide":[62],"answer":[64],"this":[66],"question":[67],"by":[68],"bounding":[69],"weighted":[71,102],"norm":[72,103],"difference":[75],"between":[76],"value":[78,93],"function":[79,94,118],"and":[90,161],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\mathcal{M}$</tex>.":[98],"The":[99],"use":[100],"allows":[104],"us":[105],"obtain":[107],"meaningful":[108],"bounds":[109],"performance":[111],"loss":[112],"even":[113],"per-step":[116,141],"is":[119,122],"unbounded.":[120],"This":[121],"contrast":[124],"much":[126],"prior":[129],"literature":[130],"which":[131],"has":[132],"largely":[133],"focused":[134],"on":[136],"case":[138],"bounded":[140],"cost.":[142],"illustrate":[144],"our":[145],"results":[146],"two":[148],"specific":[149],"instances":[150],"-":[151],"finite":[153],"MDP":[154],"inventory":[158],"linear":[164],"quadratic":[165],"regulator":[166],"problem.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-22T09:01:20.584952","created_date":"2025-10-10T00:00:00"}
