{"id":"https://openalex.org/W4415428132","doi":"https://doi.org/10.3233/faia251206","title":"Efficient Computation of Blackwell Optimal Policies Using Rational Functions","display_name":"Efficient Computation of Blackwell Optimal Policies Using Rational Functions","publication_year":2025,"publication_date":"2025-10-21","ids":{"openalex":"https://openalex.org/W4415428132","doi":"https://doi.org/10.3233/faia251206"},"language":null,"primary_location":{"id":"doi:10.3233/faia251206","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251206","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia251206","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Dibyangshu Mukherjee","orcid":null},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Dibyangshu Mukherjee","raw_affiliation_strings":["IIT Bombay, Mumbai, India; dbnshu@cse.iitb.ac.in, shivaram@cse.iitb.ac.in"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT Bombay, Mumbai, India; dbnshu@cse.iitb.ac.in, shivaram@cse.iitb.ac.in","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038200034","display_name":"Shivaram Kalyanakrishnan","orcid":null},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shivaram Kalyanakrishnan","raw_affiliation_strings":["IIT Bombay, Mumbai, India; dbnshu@cse.iitb.ac.in, shivaram@cse.iitb.ac.in"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT Bombay, Mumbai, India; dbnshu@cse.iitb.ac.in, shivaram@cse.iitb.ac.in","institution_ids":["https://openalex.org/I162827531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162827531"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.73313433,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.8634999990463257,"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"}},"topics":[{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.8634999990463257,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.8589000105857849,"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/T10050","display_name":"Multi-Criteria Decision Making","score":0.8212000131607056,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5681999921798706},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5065000057220459},{"id":"https://openalex.org/keywords/rational-expectations","display_name":"Rational expectations","score":0.47839999198913574},{"id":"https://openalex.org/keywords/optimality-criterion","display_name":"Optimality criterion","score":0.3767000138759613},{"id":"https://openalex.org/keywords/decision-theory","display_name":"Decision theory","score":0.319599986076355},{"id":"https://openalex.org/keywords/rational-function","display_name":"Rational function","score":0.29649999737739563},{"id":"https://openalex.org/keywords/linear-programming","display_name":"Linear programming","score":0.28769999742507935}],"concepts":[{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6327000260353088},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5681999921798706},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5065000057220459},{"id":"https://openalex.org/C96016098","wikidata":"https://www.wikidata.org/wiki/Q853949","display_name":"Rational expectations","level":2,"score":0.47839999198913574},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.44929999113082886},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.40790000557899475},{"id":"https://openalex.org/C2778153524","wikidata":"https://www.wikidata.org/wiki/Q4241335","display_name":"Optimality criterion","level":2,"score":0.3767000138759613},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.3237999975681305},{"id":"https://openalex.org/C28901747","wikidata":"https://www.wikidata.org/wiki/Q177571","display_name":"Decision theory","level":2,"score":0.319599986076355},{"id":"https://openalex.org/C75190567","wikidata":"https://www.wikidata.org/wiki/Q41237","display_name":"Rational function","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C3018263672","wikidata":"https://www.wikidata.org/wiki/Q1296251","display_name":"Efficient algorithm","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C31772880","wikidata":"https://www.wikidata.org/wiki/Q2666479","display_name":"Rational agent","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.25459998846054077}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia251206","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251206","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia251206","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251206","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Markov":[0],"Decision":[1],"Problems":[2],"(MDPs)":[3],"provide":[4],"a":[5,52],"foundational":[6],"framework":[7],"for":[8,73,92,111,142,147],"modelling":[9],"sequential":[10],"decision-making":[11],"across":[12],"diverse":[13],"domains,":[14],"guided":[15],"by":[16],"optimality":[17,32,40,47,59],"criteria":[18,27],"such":[19],"as":[20],"discounted":[21,31,62,171],"and":[22,54,63,113,146],"average":[23,39,64],"rewards.":[24],"However,":[25],"these":[26,49],"have":[28],"inherent":[29],"limitations:":[30],"may":[33],"overly":[34],"prioritise":[35],"short-term":[36],"rewards,":[37],"while":[38],"relies":[41],"on":[42,122],"strong":[43],"structural":[44],"assumptions.":[45],"Blackwell":[46,75,174],"addresses":[48],"challenges,":[50],"offering":[51],"robust":[53],"comprehensive":[55],"criterion":[56],"that":[57],"ensures":[58],"under":[60],"both":[61],"reward":[65],"frameworks.":[66],"Despite":[67],"its":[68],"theoretical":[69],"appeal,":[70],"existing":[71],"algorithms":[72,110,141],"computing":[74,93,143],"Optimal":[76],"(BO)":[77],"policies":[78,95],"are":[79],"computationally":[80],"expensive":[81],"or":[82],"hard":[83],"to":[84,125,172],"implement.":[85],"In":[86],"this":[87],"paper":[88],"we":[89,135,150],"describe":[90],"procedures":[91],"BO":[94,144],"using":[96],"an":[97],"ordering":[98],"of":[99,105,129],"rational":[100,123],"functions":[101,124],"in":[102],"the":[103,137,152,164,170,173],"vicinity":[104],"1.":[106],"We":[107,156],"adapt":[108],"state-of-the-art":[109],"deterministic":[112,133],"general":[114,148],"MDPs,":[115,134],"replacing":[116],"numerical":[117],"evaluations":[118],"with":[119],"symbolic":[120],"operations":[121],"derive":[126],"bounds":[127,168],"independent":[128],"bit":[130],"complexity.":[131],"For":[132],"give":[136],"first":[138,153],"strongly":[139],"polynomial-time":[140],"policies,":[145],"MDPs":[149],"obtain":[151],"subexponential-time":[154],"algorithm.":[155],"further":[157],"generalise":[158],"several":[159],"policy":[160],"iteration":[161],"algorithms,":[162],"extending":[163],"best":[165],"known":[166],"upper":[167],"from":[169],"criterion.":[175]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-24T00:00:00"}