{"id":"https://openalex.org/W2570542232","doi":"https://doi.org/10.1109/cdc.2016.7799360","title":"Robust optimal policies for Markov decision processes with safety-threshold constraints","display_name":"Robust optimal policies for Markov decision processes with safety-threshold constraints","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2570542232","doi":"https://doi.org/10.1109/cdc.2016.7799360","mag":"2570542232"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2016.7799360","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2016.7799360","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 55th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/conference_contribution/Robust_optimal_policies_for_Markov_decision_processes_with_safety-threshold_constraints/10243409","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059464456","display_name":"Rayna Dimitrova","orcid":"https://orcid.org/0009-0006-2494-8690"},"institutions":[{"id":"https://openalex.org/I4210121786","display_name":"Max Planck Institute for Software Systems","ror":"https://ror.org/02pe2kf23","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210121786"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Rayna Dimitrova","raw_affiliation_strings":["MPI-SWS, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MPI-SWS, Germany","institution_ids":["https://openalex.org/I4210121786"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100723531","display_name":"Jie Fu","orcid":"https://orcid.org/0000-0003-3147-6805"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jie Fu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Worcester Polytechnic Institute, Worcester, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Worcester Polytechnic Institute, Worcester, MA","institution_ids":["https://openalex.org/I107077323"]}]},{"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":["Department of Aerospace Engineering and Engineering Mechanics, University of Texas, Austin, TX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Aerospace Engineering and Engineering Mechanics, University of Texas, Austin, TX","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"7081","last_page":"7086"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.9958000183105469,"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"}},"topics":[{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.9958000183105469,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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":0.9810000061988831,"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/markov-decision-process","display_name":"Markov decision process","score":0.7811301350593567},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.7379777431488037},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.6281853318214417},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.6068300008773804},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5555046796798706},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4935835599899292},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47843578457832336},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.47751134634017944},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.44587093591690063},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.34145471453666687},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07433715462684631}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7811301350593567},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.7379777431488037},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.6281853318214417},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.6068300008773804},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5555046796798706},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4935835599899292},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47843578457832336},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.47751134634017944},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.44587093591690063},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34145471453666687},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07433715462684631},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","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":4,"locations":[{"id":"doi:10.1109/cdc.2016.7799360","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2016.7799360","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 55th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.whiterose.ac.uk:156433","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Proceedings Paper"},{"id":"pmh:oai:figshare.com:article/10243409","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Robust_optimal_policies_for_Markov_decision_processes_with_safety-threshold_constraints/10243409","pdf_url":null,"source":{"id":"https://openalex.org/S4306402621","display_name":"INDIGO (University of Illinois at Chicago)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I39422238","host_organization_name":"University of Illinois Chicago","host_organization_lineage":["https://openalex.org/I39422238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference contribution"},{"id":"pmh:oai:lra.le.ac.uk:2381/42337","is_oa":true,"landing_page_url":"https://ieeexplore.ieee.org/document/7799360/","pdf_url":null,"source":{"id":"https://openalex.org/S4306402365","display_name":"Leicester Research Archive (University of Leicester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I153648349","host_organization_name":"University of Leicester","host_organization_lineage":["https://openalex.org/I153648349"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/10243409","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Robust_optimal_policies_for_Markov_decision_processes_with_safety-threshold_constraints/10243409","pdf_url":null,"source":{"id":"https://openalex.org/S4306402621","display_name":"INDIGO (University of Illinois at Chicago)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I39422238","host_organization_name":"University of Illinois Chicago","host_organization_lineage":["https://openalex.org/I39422238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference contribution"},"sustainable_development_goals":[{"score":0.800000011920929,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W125973810","https://openalex.org/W1144593952","https://openalex.org/W1498432697","https://openalex.org/W1518931405","https://openalex.org/W1965878388","https://openalex.org/W1979586407","https://openalex.org/W2013614847","https://openalex.org/W2098432798","https://openalex.org/W2098597080","https://openalex.org/W2099275099","https://openalex.org/W2109909644","https://openalex.org/W2119790124","https://openalex.org/W2120967289","https://openalex.org/W2155153696","https://openalex.org/W2157807654","https://openalex.org/W2165622730","https://openalex.org/W2288565641","https://openalex.org/W6676708761","https://openalex.org/W6677778919"],"related_works":["https://openalex.org/W2096013579","https://openalex.org/W52153049","https://openalex.org/W1760611253","https://openalex.org/W1515117609","https://openalex.org/W1589140671","https://openalex.org/W4323315247","https://openalex.org/W2294884454","https://openalex.org/W3169161914","https://openalex.org/W4321379664","https://openalex.org/W2211790881"],"abstract_inverted_index":{"We":[0,115],"study":[1],"the":[2,27,38,70,117,120,123],"synthesis":[3,61],"of":[4,22,41,45,122],"robust":[5],"optimal":[6,67,89],"control":[7],"policies":[8,68],"for":[9,113],"Markov":[10,97],"decision":[11,98],"processes":[12],"with":[13],"transition":[14],"uncertainty":[15],"(UMDPs)":[16],"and":[17,32,58,85,111,119],"subject":[18],"to":[19,63,72,94],"two":[20],"types":[21],"constraints:":[23],"(i)":[24],"constraints":[25,35,108],"on":[26],"worst-case,":[28],"maximal":[29,49,102],"total":[30,50,103],"cost":[31,51,83,104],"(ii)":[33],"safety-threshold":[34,107],"that":[36],"bound":[37],"worst-case":[39],"probability":[40],"visiting":[42],"a":[43,55,59,81,92,101],"set":[44],"error":[46],"states.":[47],"For":[48,75],"constraints,":[52,78],"we":[53,79],"propose":[54],"state-augmentation":[56],"method":[57],"two-step":[60],"algorithm":[62],"generate":[64],"deterministic,":[65],"memoryless":[66],"given":[69],"reward":[71],"be":[73],"maximized.":[74],"safety":[76],"threshold":[77],"introduce":[80],"new":[82],"function":[84],"provide":[86],"an":[87,95],"approximately":[88],"solution":[90],"by":[91],"reduction":[93],"uncertain":[96],"process":[99],"under":[100],"constraint.":[105],"The":[106],"require":[109],"memory":[110],"randomization":[112],"optimality.":[114],"discuss":[116],"use":[118],"limitations":[121],"proposed":[124],"solution.":[125]},"counts_by_year":[{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}