{"id":"https://openalex.org/W3137295776","doi":"https://doi.org/10.1109/tac.2024.3384834","title":"On Minimizing Total Discounted Cost in MDPs Subject to Reachability Constraints","display_name":"On Minimizing Total Discounted Cost in MDPs Subject to Reachability Constraints","publication_year":2024,"publication_date":"2024-04-03","ids":{"openalex":"https://openalex.org/W3137295776","doi":"https://doi.org/10.1109/tac.2024.3384834","mag":"3137295776"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2024.3384834","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/tac.2024.3384834","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/A5075328109","display_name":"Yagiz Savas","orcid":"https://orcid.org/0000-0003-2976-0786"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yagiz Savas","raw_affiliation_strings":["University of Texas at Austin, Austin, TX, USA"],"raw_orcid":"https://orcid.org/0000-0003-2976-0786","affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016121500","display_name":"Christos K. Verginis","orcid":"https://orcid.org/0000-0002-4289-2866"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christos K. Verginis","raw_affiliation_strings":["University of Texas at Austin, Austin, TX, USA"],"raw_orcid":"https://orcid.org/0000-0002-4289-2866","affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103067990","display_name":"Michael Hibbard","orcid":"https://orcid.org/0000-0002-4697-4551"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Hibbard","raw_affiliation_strings":["University of Texas at Austin, Austin, TX, USA"],"raw_orcid":"https://orcid.org/0000-0002-4697-4551","affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068441112","display_name":"Ufuk Topcu","orcid":"https://orcid.org/0000-0003-0819-9985"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ufuk Topcu","raw_affiliation_strings":["University of Texas at Austin, Austin, TX, USA"],"raw_orcid":"https://orcid.org/0000-0003-0819-9985","affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":0.2778,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.5627891,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"69","issue":"9","first_page":"6466","last_page":"6473"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9984999895095825,"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":0.9984999895095825,"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/T10142","display_name":"Formal Methods in Verification","score":0.9901999831199646,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9692999720573425,"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/markov-decision-process","display_name":"Markov decision process","score":0.8197277784347534},{"id":"https://openalex.org/keywords/reachability","display_name":"Reachability","score":0.7775371074676514},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.760465145111084},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6091716289520264},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.5172191858291626},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.47932636737823486},{"id":"https://openalex.org/keywords/integer-programming","display_name":"Integer programming","score":0.46502920985221863},{"id":"https://openalex.org/keywords/linear-programming","display_name":"Linear programming","score":0.4538572430610657},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4291520416736603},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4176335036754608},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.35112613439559937},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11129409074783325},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.08394229412078857}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8197277784347534},{"id":"https://openalex.org/C136643341","wikidata":"https://www.wikidata.org/wiki/Q1361526","display_name":"Reachability","level":2,"score":0.7775371074676514},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.760465145111084},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6091716289520264},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.5172191858291626},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47932636737823486},{"id":"https://openalex.org/C56086750","wikidata":"https://www.wikidata.org/wiki/Q6042592","display_name":"Integer programming","level":2,"score":0.46502920985221863},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.4538572430610657},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4291520416736603},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4176335036754608},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.35112613439559937},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11129409074783325},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.08394229412078857},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tac.2024.3384834","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/tac.2024.3384834","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":[{"id":"https://metadata.un.org/sdg/16","score":0.7400000095367432,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G4908315546","display_name":null,"funder_award_id":"D19AP00004","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G7377845663","display_name":null,"funder_award_id":"FA9550-19-1-0169","funder_id":"https://openalex.org/F4320338294","funder_display_name":"Air Force Research Laboratory"}],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W58990062","https://openalex.org/W202180931","https://openalex.org/W1491322982","https://openalex.org/W1498432697","https://openalex.org/W1518931405","https://openalex.org/W1597160459","https://openalex.org/W1621538476","https://openalex.org/W1994584977","https://openalex.org/W2004883573","https://openalex.org/W2007442555","https://openalex.org/W2059470663","https://openalex.org/W2077789482","https://openalex.org/W2081287319","https://openalex.org/W2086965238","https://openalex.org/W2099275099","https://openalex.org/W2104849640","https://openalex.org/W2117428849","https://openalex.org/W2119567691","https://openalex.org/W2128480458","https://openalex.org/W2141481921","https://openalex.org/W2141816805","https://openalex.org/W2162087735","https://openalex.org/W2169528473","https://openalex.org/W2400458653","https://openalex.org/W2799242129","https://openalex.org/W2888279577","https://openalex.org/W2962736516","https://openalex.org/W3011543759","https://openalex.org/W3016295497","https://openalex.org/W3095977506","https://openalex.org/W3118621910","https://openalex.org/W3183867501","https://openalex.org/W6635722945","https://openalex.org/W6683951395","https://openalex.org/W6766952794"],"related_works":["https://openalex.org/W4389475841","https://openalex.org/W4241327272","https://openalex.org/W2120406836","https://openalex.org/W1996214847","https://openalex.org/W2903299703","https://openalex.org/W2117282672","https://openalex.org/W4211224558","https://openalex.org/W1672382258","https://openalex.org/W2119790124","https://openalex.org/W4281791088"],"abstract_inverted_index":{"In":[0],"this":[1],"article,":[2],"we":[3,124],"study":[4],"the":[5,24,46,66,90,108,113,145],"synthesisof":[6],"a":[7,10,20,35,39,49,77,84],"policy":[8,64,120],"in":[9,23],"Markov":[11],"decision":[12,109],"process":[13],"(MDP)":[14],"following":[15],"which":[16],"an":[17,62,93,116,126,136,148],"agent":[18],"reaches":[19],"target":[21],"state":[22],"MDP":[25],"while":[26],"minimizing":[27],"its":[28],"total":[29],"discounted":[30,40],"cost.":[31],"The":[32],"problem":[33,110],"combines":[34],"reachability":[36],"criterion":[37,42],"with":[38,51,112],"cost":[41],"and":[43,54,86,105,134],"naturally":[44],"expresses":[45],"completion":[47],"of":[48,92,115,147],"task":[50],"probabilistic":[52],"guarantees":[53],"optimal":[55,63,94,117,149],"transient":[56],"performance.":[57],"We":[58,81,96],"first":[59],"establish":[60],"that":[61,73,107],"for":[65,89,144],"considered":[67],"formulation":[68],"may":[69],"not":[70],"exist":[71],"but":[72],"there":[74],"always":[75],"exists":[76],"near-optimal":[78],"stationary":[79,102,118,150],"policy.":[80,95,152],"additionally":[82],"provide":[83,125],"necessary":[85],"sufficient":[87],"condition":[88],"existence":[91],"then":[97],"restrict":[98],"our":[99],"attention":[100],"to":[101],"deterministic":[103,119,151],"policies":[104],"show":[106],"associated":[111],"synthesis":[114,146],"is":[121],"NP-complete.":[122],"Finally,":[123],"exact":[127],"algorithm":[128,139],"based":[129,140],"on":[130,141],"mixed-integer":[131],"linear":[132,142],"programming":[133,143],"propose":[135],"efficient":[137],"approximation":[138]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}
