{"id":"https://openalex.org/W2974424662","doi":"https://doi.org/10.1109/tac.2019.2942528","title":"Information Relaxation Bounds for Partially Observed Markov Decision Processes","display_name":"Information Relaxation Bounds for Partially Observed Markov Decision Processes","publication_year":2019,"publication_date":"2019-09-20","ids":{"openalex":"https://openalex.org/W2974424662","doi":"https://doi.org/10.1109/tac.2019.2942528","mag":"2974424662"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2019.2942528","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2019.2942528","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/A5047890493","display_name":"Martin B. Haugh","orcid":"https://orcid.org/0000-0002-0823-1044"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Martin B. Haugh","raw_affiliation_strings":["Imperial College Business School, London, U.K"],"raw_orcid":"https://orcid.org/0000-0002-0823-1044","affiliations":[{"raw_affiliation_string":"Imperial College Business School, London, U.K","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076085431","display_name":"Octavio Ruiz Lacedelli","orcid":"https://orcid.org/0000-0001-6705-8336"},"institutions":[{"id":"https://openalex.org/I2802755631","display_name":"Morgan Stanley (United States)","ror":"https://ror.org/00aphdz18","country_code":"US","type":"company","lineage":["https://openalex.org/I2802755631"]},{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Octavio Ruiz Lacedelli","raw_affiliation_strings":["Department of Industrial Engineering and Operations Research, Columbia University, New York, USA","Morgan Stanley, New York, USA"],"raw_orcid":"https://orcid.org/0000-0001-6705-8336","affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering and Operations Research, Columbia University, New York, USA","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Morgan Stanley, New York, USA","institution_ids":["https://openalex.org/I2802755631"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5047890493"],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":0.578,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.76162269,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"65","issue":"8","first_page":"3256","last_page":"3271"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9988999962806702,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9988999962806702,"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/T12879","display_name":"Distributed Sensor Networks and Detection Algorithms","score":0.9861999750137329,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9603999853134155,"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":0.7860299348831177},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.7183670997619629},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.6565445065498352},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6525197625160217},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6470123529434204},{"id":"https://openalex.org/keywords/relaxation","display_name":"Relaxation (psychology)","score":0.5881373882293701},{"id":"https://openalex.org/keywords/duality","display_name":"Duality (order theory)","score":0.5814495086669922},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.49406054615974426},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.4875999987125397},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.47507160902023315},{"id":"https://openalex.org/keywords/complete-information","display_name":"Complete information","score":0.46018773317337036},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.28311413526535034},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.261685311794281},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1487947702407837},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.07002595067024231}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7860299348831177},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.7183670997619629},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.6565445065498352},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6525197625160217},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6470123529434204},{"id":"https://openalex.org/C2776029896","wikidata":"https://www.wikidata.org/wiki/Q3935810","display_name":"Relaxation (psychology)","level":2,"score":0.5881373882293701},{"id":"https://openalex.org/C2778023678","wikidata":"https://www.wikidata.org/wiki/Q554403","display_name":"Duality (order theory)","level":2,"score":0.5814495086669922},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.49406054615974426},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4875999987125397},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.47507160902023315},{"id":"https://openalex.org/C113336015","wikidata":"https://www.wikidata.org/wiki/Q574010","display_name":"Complete information","level":2,"score":0.46018773317337036},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28311413526535034},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.261685311794281},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1487947702407837},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.07002595067024231},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","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/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tac.2019.2942528","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2019.2942528","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","display_name":"Peace, Justice and strong institutions","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W58990062","https://openalex.org/W158205031","https://openalex.org/W180325379","https://openalex.org/W1511986666","https://openalex.org/W1511998054","https://openalex.org/W1539216098","https://openalex.org/W1548158210","https://openalex.org/W1755360231","https://openalex.org/W1966283062","https://openalex.org/W1973303403","https://openalex.org/W2017001821","https://openalex.org/W2020677283","https://openalex.org/W2045205720","https://openalex.org/W2065087844","https://openalex.org/W2074297971","https://openalex.org/W2079498898","https://openalex.org/W2085130871","https://openalex.org/W2098432798","https://openalex.org/W2116049533","https://openalex.org/W2137824542","https://openalex.org/W2139277921","https://openalex.org/W2143026125","https://openalex.org/W2144787803","https://openalex.org/W2151786492","https://openalex.org/W2154463167","https://openalex.org/W2155329254","https://openalex.org/W2156040550","https://openalex.org/W2169294731","https://openalex.org/W2278934889","https://openalex.org/W2478605617","https://openalex.org/W2510384539","https://openalex.org/W2542637644","https://openalex.org/W2611766878","https://openalex.org/W2739765463","https://openalex.org/W2758153130","https://openalex.org/W2902188192","https://openalex.org/W2949607913","https://openalex.org/W2963330758","https://openalex.org/W3122113998","https://openalex.org/W3124130328","https://openalex.org/W3124696154","https://openalex.org/W3125033228","https://openalex.org/W3125436659","https://openalex.org/W4239466562","https://openalex.org/W6632786116","https://openalex.org/W6695188462","https://openalex.org/W6744066508"],"related_works":["https://openalex.org/W1995828591","https://openalex.org/W4225791185","https://openalex.org/W4288405857","https://openalex.org/W2161367706","https://openalex.org/W1994682696","https://openalex.org/W4281703999","https://openalex.org/W3204119650","https://openalex.org/W1988712460","https://openalex.org/W1987390816","https://openalex.org/W2149476049"],"abstract_inverted_index":{"Partially":[0],"observed":[1],"Markov":[2,58],"decision":[3,59],"processes":[4],"(POMDPs)":[5],"are":[6,14,25,73,174,229,280],"an":[7,110],"important":[8],"class":[9],"of":[10,20,45,66,82,98,106,179,190,216,235,254],"control":[11],"problems":[12,24],"that":[13,102,156,222],"ubiquitous":[15],"in":[16,29,53,56,204,230],"a":[17,76,107],"wide":[18],"range":[19],"fields.":[21],"Unfortunately,":[22],"these":[23,46,83],"generally":[26],"intractable,":[27],"so,":[28],"general,":[30,205],"we":[31,41,88,128,141],"must":[32],"be":[33,161,240,266],"satisfied":[34],"with":[35],"suboptimal":[36],"policies.":[37],"But":[38],"how":[39],"do":[40],"evaluate":[42],"the":[43,57,64,70,90,103,114,125,136,148,166,177,180,188,191,206,252,270,288,292],"quality":[44],"policies?":[47],"This":[48,233],"question":[49],"has":[50],"been":[51],"addressed":[52],"recent":[54],"years":[55],"process":[60],"(MDP)":[61],"literature":[62],"through":[63],"use":[65,129,142,296],"information-relaxation-based":[67],"duality,":[68],"where":[69],"nonanticipativity":[71],"constraints":[72],"relaxed,":[74],"but":[75],"penalty":[77],"is":[78,97,109,219,234,256],"imposed":[79],"for":[80,118,176,187,198,227],"violations":[81],"constraints.":[84],"In":[85,169],"this":[86,170,217],"paper,":[87],"extend":[89],"information":[91],"relaxation":[92],"approach":[93],"to":[94,122,134,146,165,220,243,283,303],"POMDPs.":[95,123],"It":[96],"course":[99],"well":[100],"known":[101],"belief-state":[104,126,167,207],"formulation":[105,208],"POMDP":[108],"MDP,":[111],"and":[112,140,201,260,301],"therefore,":[113,261],"previously":[115],"developed":[116,131],"results":[117],"MDPs":[119],"also":[120,153,160,281],"apply":[121],"Under":[124],"formulation,":[127],"recently":[130],"change-of-measure":[132,172],"arguments":[133,145,173],"solve":[135],"so-called":[137,181],"inner":[138,192],"problems,":[139],"standard":[143],"filtering":[144],"identify":[147],"appropriate":[149],"Radon-Nikodym":[150],"derivatives.":[151],"We":[152,194,295],"show,":[154],"however,":[155],"dual":[157,182,196],"bounds":[158,197,275,286,289],"can":[159,239,265],"constructed":[162,276],"without":[163],"resorting":[164],"formulation.":[168],"case,":[171],"required":[175],"evaluation":[178],"feasible":[183],"penalties":[184,245,279],"rather":[185],"than":[186,287],"solution":[189],"problems.":[193],"compare":[195],"both":[199],"formulations":[200],"argue":[202],"that,":[203],"provides":[209],"tighter":[210,285],"bounds.":[211],"The":[212],"second":[213],"main":[214],"contribution":[215],"paper":[218],"show":[221],"several":[223],"value":[224],"function":[225],"approximations":[226],"POMDPs":[228],"fact":[231],"supersolutions.":[232],"interest":[236],"because":[237],"it":[238],"particularly":[241],"advantageous":[242],"construct":[244],"from":[246,277,298],"supersolutions,":[247],"since":[248],"absolute":[249],"continuity":[250],"(of":[251],"change":[253],"measure)":[255],"no":[257],"longer":[258],"required,":[259],"significant":[262],"variance":[263],"reduction":[264],"achieved":[267],"when":[268],"estimating":[269],"duality":[271],"gap":[272],"directly.":[273],"Dual":[274],"supersolution-based":[278],"guaranteed":[282],"provide":[284],"provided":[290],"by":[291],"supersolutions":[293],"themselves.":[294],"applications":[297],"robotic":[299],"navigation":[300],"telecommunication":[302],"demonstrate":[304],"our":[305],"results.":[306]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}