{"id":"https://openalex.org/W4400946760","doi":"https://doi.org/10.23919/ecc64448.2024.10591108","title":"On the Convergence of TD-Learning on Markov Reward Processes with Hidden States","display_name":"On the Convergence of TD-Learning on Markov Reward Processes with Hidden States","publication_year":2024,"publication_date":"2024-06-25","ids":{"openalex":"https://openalex.org/W4400946760","doi":"https://doi.org/10.23919/ecc64448.2024.10591108"},"language":"en","primary_location":{"id":"doi:10.23919/ecc64448.2024.10591108","is_oa":false,"landing_page_url":"https://doi.org/10.23919/ecc64448.2024.10591108","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 European Control Conference (ECC)","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":null,"display_name":"Mohsen Amiri","orcid":null},"institutions":[{"id":"https://openalex.org/I161593684","display_name":"Stockholm University","ror":"https://ror.org/05f0yaq80","country_code":"SE","type":"education","lineage":["https://openalex.org/I161593684"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Mohsen Amiri","raw_affiliation_strings":["Stockholm University,Department of Computer and System Science,Stockholm,Sweden,11419"],"affiliations":[{"raw_affiliation_string":"Stockholm University,Department of Computer and System Science,Stockholm,Sweden,11419","institution_ids":["https://openalex.org/I161593684"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054704457","display_name":"Sindri Magn\u00fasson","orcid":"https://orcid.org/0000-0002-6617-8683"},"institutions":[{"id":"https://openalex.org/I161593684","display_name":"Stockholm University","ror":"https://ror.org/05f0yaq80","country_code":"SE","type":"education","lineage":["https://openalex.org/I161593684"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Sindri Magn\u00fasson","raw_affiliation_strings":["Stockholm University,Department of Computer and System Science,Stockholm,Sweden,11419"],"affiliations":[{"raw_affiliation_string":"Stockholm University,Department of Computer and System Science,Stockholm,Sweden,11419","institution_ids":["https://openalex.org/I161593684"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I161593684"],"apc_list":null,"apc_paid":null,"fwci":0.319,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55181377,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2097","last_page":"2104"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14420","display_name":"Advanced Research in Systems and Signal Processing","score":0.6715999841690063,"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/T14420","display_name":"Advanced Research in Systems and Signal Processing","score":0.6715999841690063,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.7519362568855286},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.593278169631958},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5834029316902161},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5592524409294128},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.47301366925239563},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45877397060394287},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34670591354370117},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18505769968032837},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1460258662700653},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.10435876250267029}],"concepts":[{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7519362568855286},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.593278169631958},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5834029316902161},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5592524409294128},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.47301366925239563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45877397060394287},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34670591354370117},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18505769968032837},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1460258662700653},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.10435876250267029},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/ecc64448.2024.10591108","is_oa":false,"landing_page_url":"https://doi.org/10.23919/ecc64448.2024.10591108","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 European Control Conference (ECC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.75,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G3356834494","display_name":null,"funder_award_id":"2020\u201303607","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"}],"funders":[{"id":"https://openalex.org/F4320322581","display_name":"Vetenskapsr\u00e5det","ror":"https://ror.org/03zttf063"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W232548544","https://openalex.org/W1978790532","https://openalex.org/W2011418219","https://openalex.org/W2139418546","https://openalex.org/W2261885288","https://openalex.org/W2798333393","https://openalex.org/W2885549115","https://openalex.org/W2963616027","https://openalex.org/W2964957478","https://openalex.org/W2997350486","https://openalex.org/W3025787433","https://openalex.org/W3147254695","https://openalex.org/W4205326910","https://openalex.org/W4250389103","https://openalex.org/W4296913591","https://openalex.org/W4377692738","https://openalex.org/W6758937863","https://openalex.org/W6779756043"],"related_works":["https://openalex.org/W2364370872","https://openalex.org/W2053269318","https://openalex.org/W2025614924","https://openalex.org/W2294335174","https://openalex.org/W2097963413","https://openalex.org/W2379651310","https://openalex.org/W2113019827","https://openalex.org/W1541249122","https://openalex.org/W2413828414","https://openalex.org/W2367222340"],"abstract_inverted_index":{"We":[0,91],"investigate":[1],"the":[2,36,39,69,73,77,81,84,87,100,104,115,126,131,135,141,144,149,167,170],"convergence":[3,168],"properties":[4,128],"of":[5,103,125,129,140,169],"Temporal":[6],"Difference":[7],"(TD)":[8],"Learning":[9],"on":[10,99,114,152],"Markov":[11,52,57,132],"Reward":[12],"Processes":[13],"(MRPs)":[14],"with":[15,35],"new":[16],"structures":[17],"for":[18],"incorporating":[19],"hidden":[20,33,42,70,78,138],"state":[21,26,74,79],"information.":[22],"In":[23],"particular,":[24],"each":[25],"is":[27,64],"characterized":[28],"by":[29],"both":[30,130],"observable":[31,40,101,136],"and":[32,41,54,137],"components,":[34],"assumption":[37],"that":[38,61,93],"parts":[43,139],"are":[44],"statistically":[45],"independent.":[46],"This":[47],"setup":[48],"differs":[49],"from":[50,72],"Hidden":[51],"Models":[53],"Partially":[55],"Observable":[56],"Decision":[58],"Models,":[59],"in":[60,123,156,172],"here":[62],"it":[63],"not":[65],"possible":[66],"to":[67,107],"infer":[68],"information":[71],"observations.":[75],"Nevertheless,":[76],"influences":[80],"MRP":[82],"through":[83,163],"rewards,":[85],"rendering":[86],"reward":[88],"sequence":[89],"non-Markovian.":[90],"prove":[92],"TD":[94],"learning,":[95],"when":[96],"applied":[97],"only":[98],"part":[102],"states,":[105],"converges":[106],"a":[108],"fixed":[109,121],"point":[110,122],"under":[111],"mild":[112],"assumptions":[113],"step-size.":[116],"Furthermore,":[117,158],"we":[118,147,159],"characterize":[119],"this":[120],"terms":[124],"statistical":[127],"chains":[133],"representing":[134],"states.":[142],"Beyond":[143],"theoretical":[145],"results,":[146],"illustrate":[148],"novel":[150],"structure":[151],"two":[153],"application":[154],"setups":[155],"communications.":[157],"validate":[160],"our":[161],"results":[162],"experimental":[164],"evidence,":[165],"showcasing":[166],"algorithm":[171],"practice.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}