{"id":"https://openalex.org/W4390480853","doi":"https://doi.org/10.1109/tpami.2023.3348460","title":"Semi-Infinitely Constrained Markov Decision Processes and Provably Efficient Reinforcement Learning","display_name":"Semi-Infinitely Constrained Markov Decision Processes and Provably Efficient Reinforcement Learning","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4390480853","doi":"https://doi.org/10.1109/tpami.2023.3348460","pmid":"https://pubmed.ncbi.nlm.nih.gov/38163315"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2023.3348460","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3348460","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5101891217","display_name":"Liangyu Zhang","orcid":"https://orcid.org/0009-0005-2731-3941"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liangyu Zhang","raw_affiliation_strings":["Academy for Advanced Interdisciplinary Studies, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-2731-3941","affiliations":[{"raw_affiliation_string":"Academy for Advanced Interdisciplinary Studies, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100681631","display_name":"Peng Yang","orcid":"https://orcid.org/0000-0002-0063-3102"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Peng","raw_affiliation_strings":["School of Mathematical Sciences, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0063-3102","affiliations":[{"raw_affiliation_string":"School of Mathematical Sciences, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101838606","display_name":"Wenhao Yang","orcid":"https://orcid.org/0000-0001-6228-8917"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhao Yang","raw_affiliation_strings":["Academy for Advanced Interdisciplinary Studies, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6228-8917","affiliations":[{"raw_affiliation_string":"Academy for Advanced Interdisciplinary Studies, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100393616","display_name":"Zhihua Zhang","orcid":"https://orcid.org/0000-0003-3165-5213"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihua Zhang","raw_affiliation_strings":["School of Mathematical Sciences, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3165-5213","affiliations":[{"raw_affiliation_string":"School of Mathematical Sciences, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":1.8589,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.86261164,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"46","issue":"5","first_page":"3722","last_page":"3735"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T10142","display_name":"Formal Methods in Verification","score":0.9840999841690063,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9684000015258789,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.9055641889572144},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.8533943891525269},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6616688370704651},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5482169389724731},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4839242100715637},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4814421534538269},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.47619402408599854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.471597284078598},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.43966299295425415},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35894668102264404},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21899297833442688}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9055641889572144},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8533943891525269},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6616688370704651},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5482169389724731},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4839242100715637},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4814421534538269},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.47619402408599854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.471597284078598},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.43966299295425415},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35894668102264404},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21899297833442688},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2023.3348460","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3348460","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:38163315","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38163315","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6100000143051147,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G3819207089","display_name":null,"funder_award_id":"12271011","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G512795570","display_name":null,"funder_award_id":"12350001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":76,"referenced_works":["https://openalex.org/W137390859","https://openalex.org/W147998453","https://openalex.org/W177890044","https://openalex.org/W306289341","https://openalex.org/W1144593952","https://openalex.org/W1845972764","https://openalex.org/W1969276875","https://openalex.org/W1977655452","https://openalex.org/W1991334712","https://openalex.org/W2005136695","https://openalex.org/W2027577301","https://openalex.org/W2027579135","https://openalex.org/W2049355922","https://openalex.org/W2054709617","https://openalex.org/W2062687608","https://openalex.org/W2064244768","https://openalex.org/W2064380469","https://openalex.org/W2075887074","https://openalex.org/W2083247753","https://openalex.org/W2089998287","https://openalex.org/W2101508998","https://openalex.org/W2104756045","https://openalex.org/W2111492941","https://openalex.org/W2121703796","https://openalex.org/W2123117904","https://openalex.org/W2123859926","https://openalex.org/W2147373987","https://openalex.org/W2178744658","https://openalex.org/W2283884363","https://openalex.org/W2415697701","https://openalex.org/W2551641323","https://openalex.org/W2736601468","https://openalex.org/W2804791273","https://openalex.org/W2885558587","https://openalex.org/W2902907165","https://openalex.org/W2963568654","https://openalex.org/W2971587637","https://openalex.org/W2982316857","https://openalex.org/W2994712737","https://openalex.org/W2998619042","https://openalex.org/W2998993395","https://openalex.org/W3007099432","https://openalex.org/W3041202696","https://openalex.org/W3045730640","https://openalex.org/W3082459541","https://openalex.org/W3171210634","https://openalex.org/W3172220074","https://openalex.org/W3189256393","https://openalex.org/W3209135762","https://openalex.org/W3210638057","https://openalex.org/W4206497039","https://openalex.org/W4206742934","https://openalex.org/W4226278401","https://openalex.org/W4282916382","https://openalex.org/W4287829052","https://openalex.org/W6638018090","https://openalex.org/W6677984395","https://openalex.org/W6683195989","https://openalex.org/W6683204974","https://openalex.org/W6729229454","https://openalex.org/W6737893269","https://openalex.org/W6741002519","https://openalex.org/W6751725685","https://openalex.org/W6761973403","https://openalex.org/W6767941141","https://openalex.org/W6771280675","https://openalex.org/W6772593463","https://openalex.org/W6774521036","https://openalex.org/W6776530296","https://openalex.org/W6779812412","https://openalex.org/W6780486084","https://openalex.org/W6796690604","https://openalex.org/W6796728928","https://openalex.org/W6810738896","https://openalex.org/W6838881121","https://openalex.org/W6990670832"],"related_works":["https://openalex.org/W1985560493","https://openalex.org/W2386410636","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3168977894","https://openalex.org/W3096874164","https://openalex.org/W2357975469","https://openalex.org/W2937181779","https://openalex.org/W2182304831","https://openalex.org/W2145363145"],"abstract_inverted_index":{"We":[0,42,154,169],"propose":[1],"a":[2,24,30,61,81,103],"novel":[3],"generalization":[4],"of":[5,26,29,33,39,69,134],"constrained":[6,16,150],"Markov":[7,17],"decision":[8,18],"processes":[9],"(CMDPs)":[10],"that":[11,51,182],"we":[12,22,52,73,115,137],"call":[13],"the":[14,37,70,76,90,95,110,120,125,129,132,139,177],"semi-infinitely":[15,83,145],"process":[19],"(SICMDP).":[20],"Particularly,":[21],"consider":[23],"continuum":[25],"constraints":[27,34],"instead":[28],"finite":[31],"number":[32],"as":[35,55],"in":[36,94],"case":[38],"ordinary":[40],"CMDPs.":[41],"also":[43,170],"devise":[44],"two":[45],"reinforcement":[46,63,77,151,196],"learning":[47,64,78,152,197],"algorithms":[48,185],"for":[49,158],"SICMDPs":[50],"refer":[53],"to":[54,98,119,123,141,148,175,188],"SI-CMBRL":[56,59,159],"and":[57,87,160,166,180],"SI-CPO.":[58],"is":[60,102],"model-based":[62],"algorithm.":[65,106],"Given":[66],"an":[67],"estimate":[68],"transition":[71],"model,":[72],"first":[74,140],"transform":[75],"problem":[79,86],"into":[80],"linear":[82],"programming":[84,146],"(LSIP)":[85],"then":[88],"use":[89],"dual":[91],"exchange":[92],"method":[93],"LSIP":[96],"literature":[97],"solve":[99,149,189],"it.":[100],"SI-CPO":[101],"policy":[104,121],"optimization":[105],"Borrowing":[107],"ideas":[108],"from":[109,144],"cooperative":[111],"stochastic":[112],"approximation":[113],"approach,":[114],"make":[116],"alternative":[117],"updates":[118],"parameters":[122],"maximize":[124],"reward":[126],"or":[127],"minimize":[128],"cost.":[130],"To":[131],"best":[133],"our":[135,183],"knowledge,":[136],"are":[138,186],"apply":[142],"tools":[143],"(SIP)":[147],"problems.":[153],"present":[155],"theoretical":[156],"analysis":[157],"SI-CPO,":[161],"identifying":[162],"their":[163],"iteration":[164],"complexity":[165],"sample":[167],"complexity.":[168],"conduct":[171],"extensive":[172],"numerical":[173],"experiments":[174],"illustrate":[176],"SICMDP":[178],"model":[179],"demonstrate":[181],"proposed":[184],"able":[187],"complex":[190],"control":[191],"tasks":[192],"leveraging":[193],"modern":[194],"deep":[195],"techniques.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}