{"id":"https://openalex.org/W2135915258","doi":"https://doi.org/10.1109/cdc.2004.1429442","title":"Partially observable Markov decision processes with reward information","display_name":"Partially observable Markov decision processes with reward information","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W2135915258","doi":"https://doi.org/10.1109/cdc.2004.1429442","mag":"2135915258"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2004.1429442","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2004.1429442","pdf_url":null,"source":{"id":"https://openalex.org/S4363608267","display_name":"2004 43rd IEEE Conference on Decision and Control (CDC) (IEEE Cat. No.04CH37601)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 43rd IEEE Conference on Decision and Control (CDC) (IEEE Cat. No.04CH37601)","raw_type":"proceedings-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/A5100635237","display_name":"Xi\u2010Ren Cao","orcid":"https://orcid.org/0000-0001-5165-8804"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Xi-Ren Cao","raw_affiliation_strings":["Dept. of Electr. & Electron. Eng. Hong Kong Univ. of Sci. & Technol., China"],"affiliations":[{"raw_affiliation_string":"Dept. of Electr. & Electron. Eng. Hong Kong Univ. of Sci. & Technol., China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101505539","display_name":"Xianping Guo","orcid":"https://orcid.org/0000-0001-6954-5947"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xianping Guo","raw_affiliation_strings":["Sun Yat-Sen University"],"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100635237"],"corresponding_institution_ids":["https://openalex.org/I200769079"],"apc_list":null,"apc_paid":null,"fwci":1.0102,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.76648097,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"4393","last_page":"4398 Vol.4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9873999953269958,"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/T10142","display_name":"Formal Methods in Verification","score":0.9851999878883362,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.9590336084365845},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.8885962963104248},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7392945289611816},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.6767932772636414},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.555591344833374},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5204237103462219},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4937151372432709},{"id":"https://openalex.org/keywords/decision-process","display_name":"Decision process","score":0.472564160823822},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.42506396770477295},{"id":"https://openalex.org/keywords/probability-distribution","display_name":"Probability distribution","score":0.41534459590911865},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.337472140789032},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.31730005145072937},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.19122472405433655},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.18749618530273438},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.17103227972984314},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16601771116256714},{"id":"https://openalex.org/keywords/management-science","display_name":"Management science","score":0.08503410220146179},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07141932845115662}],"concepts":[{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.9590336084365845},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.8885962963104248},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7392945289611816},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.6767932772636414},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.555591344833374},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5204237103462219},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4937151372432709},{"id":"https://openalex.org/C2984634286","wikidata":"https://www.wikidata.org/wiki/Q1331926","display_name":"Decision process","level":2,"score":0.472564160823822},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.42506396770477295},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.41534459590911865},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.337472140789032},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.31730005145072937},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.19122472405433655},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.18749618530273438},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.17103227972984314},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16601771116256714},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.08503410220146179},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07141932845115662},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cdc.2004.1429442","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2004.1429442","pdf_url":null,"source":{"id":"https://openalex.org/S4363608267","display_name":"2004 43rd IEEE Conference on Decision and Control (CDC) (IEEE Cat. No.04CH37601)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 43rd IEEE Conference on Decision and Control (CDC) (IEEE Cat. No.04CH37601)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-43745","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-43745","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W41599142","https://openalex.org/W1531253382","https://openalex.org/W1563317173","https://openalex.org/W1967037758","https://openalex.org/W1972176367","https://openalex.org/W2010654234","https://openalex.org/W2028586524","https://openalex.org/W2029561387","https://openalex.org/W2040434095","https://openalex.org/W2043378258","https://openalex.org/W2044549125","https://openalex.org/W2059608296","https://openalex.org/W2065087844","https://openalex.org/W2068782949","https://openalex.org/W2069065005","https://openalex.org/W2071370395","https://openalex.org/W2075379212","https://openalex.org/W2095267417","https://openalex.org/W2107338824","https://openalex.org/W2115308494","https://openalex.org/W2119567691","https://openalex.org/W2175602944","https://openalex.org/W2334404018","https://openalex.org/W2334732686","https://openalex.org/W2334782222","https://openalex.org/W4210545817","https://openalex.org/W4242780150","https://openalex.org/W4245744559"],"related_works":["https://openalex.org/W2999848267","https://openalex.org/W2096013579","https://openalex.org/W52153049","https://openalex.org/W1760611253","https://openalex.org/W1589140671","https://openalex.org/W1515117609","https://openalex.org/W4323315247","https://openalex.org/W131709709","https://openalex.org/W2294884454","https://openalex.org/W3169161914"],"abstract_inverted_index":{"In":[0],"a":[1,55],"partially":[2,86],"observable":[3,87],"Markov":[4,88],"decision":[5,89],"process":[6],"(POMDP),":[7],"if":[8],"the":[9,18,25,33,37,45,74,95,102],"reward":[10,20,96,103],"can":[11,40],"be":[12,41],"observed":[13,19],"at":[14,104],"each":[15,105],"step,":[16],"then":[17],"history":[21],"contains":[22],"information":[23,34],"for":[24,85],"unknown":[26],"state.":[27],"This":[28],"information,":[29],"in":[30,36],"addition":[31],"to":[32,43,81],"contained":[35],"observation":[38,75,79],"history,":[39],"used":[42],"update":[44],"state":[46],"probability":[47],"distribution.":[48],"The":[49,77],"policy":[50,57,62,70],"thus":[51],"obtained":[52],"is":[53,98,107],"called":[54],"reward-information":[56],"(RI-policy);":[58],"an":[59],"optimal":[60,69],"RI":[61],"performs":[63],"no":[64],"worse":[65],"than":[66],"any":[67],"normal":[68],"depending":[71,92],"only":[72],"on":[73,93],"history.":[76],"above":[78],"leads":[80],"four":[82],"different":[83],"problem-formulations":[84],"processes":[90],"(POMDPs)":[91],"whether":[94,101],"function":[97],"known":[99],"and":[100],"step":[106],"observable.":[108]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}