{"id":"https://openalex.org/W4413393295","doi":"https://doi.org/10.23919/acc63710.2025.11107856","title":"Maximum A Posteriori Least-Squares Temporal Difference","display_name":"Maximum A Posteriori Least-Squares Temporal Difference","publication_year":2025,"publication_date":"2025-07-08","ids":{"openalex":"https://openalex.org/W4413393295","doi":"https://doi.org/10.23919/acc63710.2025.11107856"},"language":"en","primary_location":{"id":"doi:10.23919/acc63710.2025.11107856","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc63710.2025.11107856","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 American Control Conference (ACC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pure.tue.nl/ws/files/355810766/ACC2025_MAP_LSTD_RvZ_final.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093745180","display_name":"R.A.C. van Zuijlen","orcid":null},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"R.A.C. van Zuijlen","raw_affiliation_strings":["Eindhoven University of Technology,Control Systems Technology Section,Dep. of Mechanical Eng.,The Netherlands"],"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology,Control Systems Technology Section,Dep. of Mechanical Eng.,The Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013274345","display_name":"Duarte Antunes","orcid":"https://orcid.org/0000-0003-3047-9334"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"D.J. Antunes","raw_affiliation_strings":["Eindhoven University of Technology,Control Systems Technology Section,Dep. of Mechanical Eng.,The Netherlands"],"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology,Control Systems Technology Section,Dep. of Mechanical Eng.,The Netherlands","institution_ids":["https://openalex.org/I83019370"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5093745180"],"corresponding_institution_ids":["https://openalex.org/I83019370"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25054829,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3533","last_page":"3538"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.5067999958992004,"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"}},"topics":[{"id":"https://openalex.org/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.5067999958992004,"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"}},{"id":"https://openalex.org/T12879","display_name":"Distributed Sensor Networks and Detection Algorithms","score":0.4828999936580658,"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"}},{"id":"https://openalex.org/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.4341999888420105,"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/maximum-a-posteriori-estimation","display_name":"Maximum a posteriori estimation","score":0.6842405200004578},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.6004327535629272},{"id":"https://openalex.org/keywords/least-squares-function-approximation","display_name":"Least-squares function approximation","score":0.5592696070671082},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4482536315917969},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.44004014134407043},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.4105273485183716},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.3140708804130554},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.04238802194595337}],"concepts":[{"id":"https://openalex.org/C9810830","wikidata":"https://www.wikidata.org/wiki/Q635384","display_name":"Maximum a posteriori estimation","level":3,"score":0.6842405200004578},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.6004327535629272},{"id":"https://openalex.org/C9936470","wikidata":"https://www.wikidata.org/wiki/Q6510405","display_name":"Least-squares function approximation","level":3,"score":0.5592696070671082},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4482536315917969},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.44004014134407043},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.4105273485183716},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.3140708804130554},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.04238802194595337},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23919/acc63710.2025.11107856","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc63710.2025.11107856","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 American Control Conference (ACC)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.tue.nl:openaire_cris_publications/b0bda8b7-cbd8-4bb1-a157-2284d71da364","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/b0bda8b7-cbd8-4bb1-a157-2284d71da364","pdf_url":"https://pure.tue.nl/ws/files/355810766/ACC2025_MAP_LSTD_RvZ_final.pdf","source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"van Zuijlen, R A C & Guerreiro Tom\u00e9 Antunes, D J 2025, Maximum A Posteriori Least-Squares Temporal Difference. in 2025 American Control Conference, ACC 2025., 11107856, Institute of Electrical and Electronics Engineers, pp. 3533-3538, 2025 American Control Conference, ACC 2025, Denver, Colorado, United States, 8/07/25. https://doi.org/10.23919/ACC63710.2025.11107856","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:pure.tue.nl:openaire_cris_publications/b0bda8b7-cbd8-4bb1-a157-2284d71da364","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/b0bda8b7-cbd8-4bb1-a157-2284d71da364","pdf_url":"https://pure.tue.nl/ws/files/355810766/ACC2025_MAP_LSTD_RvZ_final.pdf","source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"van Zuijlen, R A C & Guerreiro Tom\u00e9 Antunes, D J 2025, Maximum A Posteriori Least-Squares Temporal Difference. in 2025 American Control Conference, ACC 2025., 11107856, Institute of Electrical and Electronics Engineers, pp. 3533-3538, 2025 American Control Conference, ACC 2025, Denver, Colorado, United States, 8/07/25. https://doi.org/10.23919/ACC63710.2025.11107856","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413393295.pdf","grobid_xml":"https://content.openalex.org/works/W4413393295.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W2019172585","https://openalex.org/W2056859449","https://openalex.org/W2100969003","https://openalex.org/W2123979492","https://openalex.org/W2132351269","https://openalex.org/W2236244207","https://openalex.org/W3121342653","https://openalex.org/W4213251304","https://openalex.org/W4246906609","https://openalex.org/W4387531468"],"related_works":["https://openalex.org/W1503532423","https://openalex.org/W2150865841","https://openalex.org/W1967494390","https://openalex.org/W245717845","https://openalex.org/W2138865713","https://openalex.org/W3013496002","https://openalex.org/W2169353922","https://openalex.org/W2465363361","https://openalex.org/W2896820906","https://openalex.org/W2101542441"],"abstract_inverted_index":{"Least-squares":[0],"Temporal":[1],"Difference":[2],"(LSTD)":[3],"is":[4,21,80,89,127,150],"a":[5,14,63,100,165,197],"model-free":[6],"method":[7,79,126,174],"to":[8,23,82,91,124,128],"estimate":[9],"the":[10,25,30,38,53,58,76,85,93,108,130,142,152,178,181,187],"cost/value":[11,39],"function":[12,40,110,184],"of":[13,29,52,57,104,144,180],"Markov":[15],"Decision":[16],"Process":[17],"(MDP).":[18],"Interestingly,":[19],"it":[20,88,117],"equivalent":[22,90],"estimating":[24,75,92],"state":[26,54,94,132],"transition":[27,55,95],"probabilities":[28,56,96],"MDP":[31],"through":[32,98],"Maximum":[33,99],"Likelihood":[34],"(ML)":[35],"and":[36,106,137,185],"computing":[37,107],"with":[41,111,134],"(model-based)":[42],"policy":[43,112],"evaluation.":[44,113],"However,":[45],"LSTD":[46,83],"does":[47],"not":[48],"incorporate":[49],"prior":[50,71,139,153,193],"knowledge":[51,72,140,194],"MDP.":[59],"This":[60,78],"paper":[61],"proposes":[62],"data-based":[64],"method,":[65],"coined":[66],"MAP-LSTD,":[67],"that":[68,87,151],"incorporates":[69],"such":[70],"without":[73],"explicitly":[74],"model.":[77],"analogous":[81],"in":[84,141],"sense":[86],"(model)":[97],"Posteriori":[101],"(MAP)":[102],"instead":[103],"ML":[105],"cost":[109,183],"Moreover,":[114],"as":[115],"LSTD,":[116],"can":[118,154,175],"be":[119,155],"implemented":[120],"recursively.":[121],"The":[122],"key":[123],"our":[125,173],"model":[129],"unknown":[131],"distributions":[133,136],"Dirichlet":[135],"encapsulate":[138],"parameters":[143],"these":[145],"distributions.":[146],"An":[147],"important":[148],"concomitant":[149],"obtained":[156],"from":[157,196],"previous":[158],"data":[159],"samples":[160],"and/or":[161],"simulated":[162],"samples,":[163],"leveraging":[164],"model/simulator.":[166,198],"Through":[167],"an":[168],"example,":[169],"we":[170],"illustrate":[171],"how":[172],"speed":[176],"up":[177],"convergence":[179],"estimated":[182],"reduce":[186],"estimation":[188],"error":[189],"significantly":[190],"by":[191],"exploiting":[192],"derived":[195]},"counts_by_year":[],"updated_date":"2026-03-17T17:19:04.345684","created_date":"2025-10-10T00:00:00"}