{"id":"https://openalex.org/W4315489007","doi":"https://doi.org/10.1109/cdc51059.2022.9993165","title":"Near Optimality of Finite Memory Policies for POMPDs with Continuous Spaces","display_name":"Near Optimality of Finite Memory Policies for POMPDs with Continuous Spaces","publication_year":2022,"publication_date":"2022-12-06","ids":{"openalex":"https://openalex.org/W4315489007","doi":"https://doi.org/10.1109/cdc51059.2022.9993165"},"language":"en","primary_location":{"id":"doi:10.1109/cdc51059.2022.9993165","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cdc51059.2022.9993165","pdf_url":null,"source":{"id":"https://openalex.org/S4363607710","display_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","raw_type":"proceedings-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/A5101664274","display_name":"Ali\u0307 Devran Kara","orcid":"https://orcid.org/0000-0001-8119-6620"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ali Devran Kara","raw_affiliation_strings":["University of Michigan,Department of Mathematics,Ann Arbor,USA","Department of Mathematics, University of Michigan, Ann Arbor, USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan,Department of Mathematics,Ann Arbor,USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"Department of Mathematics, University of Michigan, Ann Arbor, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005237318","display_name":"Erhan Bayraktar","orcid":"https://orcid.org/0000-0002-1926-4570"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Erhan Bayraktar","raw_affiliation_strings":["University of Michigan,Department of Mathematics,Ann Arbor,USA","Department of Mathematics, University of Michigan, Ann Arbor, USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan,Department of Mathematics,Ann Arbor,USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"Department of Mathematics, University of Michigan, Ann Arbor, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005401257","display_name":"Serdar Y\u00fcksel","orcid":"https://orcid.org/0000-0001-6099-5001"},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Serdar Yuksel","raw_affiliation_strings":["Queen’s University,Department of Mathematics and Statistics,Kingston,Canada"],"affiliations":[{"raw_affiliation_string":"Queen’s University,Department of Mathematics and Statistics,Kingston,Canada","institution_ids":["https://openalex.org/I204722609"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101664274"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":0.1039,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.34394527,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"7","issue":null,"first_page":"2301","last_page":"2306"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9864000082015991,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9864000082015991,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9854999780654907,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9815000295639038,"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/discretization","display_name":"Discretization","score":0.7402909994125366},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7368983030319214},{"id":"https://openalex.org/keywords/uncountable-set","display_name":"Uncountable set","score":0.6674279570579529},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6111025810241699},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5389609336853027},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5171093940734863},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.50718092918396},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4848705232143402},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4726152718067169},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.46883195638656616},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.4584940969944},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.45816829800605774},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.45238780975341797},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.44795480370521545},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.43182846903800964},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3502216935157776},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.17886903882026672},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.12042874097824097},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.0852658748626709}],"concepts":[{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.7402909994125366},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7368983030319214},{"id":"https://openalex.org/C142399903","wikidata":"https://www.wikidata.org/wiki/Q1128796","display_name":"Uncountable set","level":3,"score":0.6674279570579529},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6111025810241699},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5389609336853027},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5171093940734863},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.50718092918396},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4848705232143402},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4726152718067169},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.46883195638656616},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.4584940969944},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.45816829800605774},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.45238780975341797},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.44795480370521545},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.43182846903800964},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3502216935157776},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.17886903882026672},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.12042874097824097},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0852658748626709},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C110729354","wikidata":"https://www.wikidata.org/wiki/Q185478","display_name":"Countable set","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc51059.2022.9993165","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cdc51059.2022.9993165","pdf_url":null,"source":{"id":"https://openalex.org/S4363607710","display_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"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":36,"referenced_works":["https://openalex.org/W1636455720","https://openalex.org/W1966208686","https://openalex.org/W1985489506","https://openalex.org/W1991665457","https://openalex.org/W2029546215","https://openalex.org/W2059608296","https://openalex.org/W2065087844","https://openalex.org/W2110962519","https://openalex.org/W2113456749","https://openalex.org/W2125848092","https://openalex.org/W2128823230","https://openalex.org/W2144088174","https://openalex.org/W2156950870","https://openalex.org/W2158907787","https://openalex.org/W2549182383","https://openalex.org/W2802739963","https://openalex.org/W2963272571","https://openalex.org/W2964034900","https://openalex.org/W2974631764","https://openalex.org/W2998102890","https://openalex.org/W3047409223","https://openalex.org/W3136541527","https://openalex.org/W3205387731","https://openalex.org/W4213251304","https://openalex.org/W4221158689","https://openalex.org/W4230410498","https://openalex.org/W4239466562","https://openalex.org/W4287640641","https://openalex.org/W4294291086","https://openalex.org/W4311128572","https://openalex.org/W6629836980","https://openalex.org/W6636732284","https://openalex.org/W6674155736","https://openalex.org/W6681718981","https://openalex.org/W6791431420","https://openalex.org/W6809717773"],"related_works":["https://openalex.org/W2100222222","https://openalex.org/W4388236136","https://openalex.org/W2807018115","https://openalex.org/W4200250224","https://openalex.org/W2126560268","https://openalex.org/W2285658092","https://openalex.org/W2482498454","https://openalex.org/W2947128950","https://openalex.org/W1996326480","https://openalex.org/W185460758"],"abstract_inverted_index":{"We":[0,79,107],"study":[1,24],"an":[2,51],"approximation":[3,40,52,140],"method":[4],"for":[5,42,102],"partially":[6],"observed":[7,63,135],"Markov":[8],"decision":[9],"processes":[10],"(POMDPs)":[11],"with":[12],"continuous":[13],"spaces.":[14],"Belief":[15],"MDP":[16,65,136],"reduction":[17],"has":[18],"been":[19],"the":[20,56,73,82,93,103,128,132,139],"standard":[21],"approach":[22],"to":[23,28,127],"POMDPs,":[25],"which,":[26],"due":[27],"its":[29,125],"uncountable":[30],"state":[31,105],"space":[32,58],"and":[33,59,76,95,123],"strict":[34],"regularity":[35,90],"properties":[36],"however,":[37],"requires":[38],"rigorous":[39],"methods":[41],"practical":[43],"applications.":[44],"In":[45],"this":[46],"work,":[47],"we":[48],"focus":[49],"on":[50,92],"procedure":[53],"via":[54],"discretizing":[55],"observation":[57],"constructing":[60],"a":[61,68,110,116],"fully":[62,134],"finite":[64,69,117,133],"model":[66],"using":[67,138],"length":[70],"history":[71],"of":[72,119,131],"discrete":[74],"observations":[75],"control":[77],"actions.":[78],"show":[80],"that":[81,114],"resulting":[83],"policy":[84],"is":[85],"nearly":[86],"optimal":[87],"under":[88,96],"some":[89],"assumptions":[91],"channel,":[94],"certain":[97],"controlled":[98],"filter":[99],"stability":[100],"requirements":[101],"hidden":[104],"process.":[106],"also":[108],"provide":[109],"Q":[111],"learning":[112],"algorithm":[113],"uses":[115],"memory":[118],"discretized":[120],"information":[121],"variables,":[122],"prove":[124],"convergence":[126],"optimality":[129],"equation":[130],"constructed":[137],"method.":[141]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}