{"id":"https://openalex.org/W4382936420","doi":"https://doi.org/10.23919/acc55779.2023.10155792","title":"Belief State Actor-Critic Algorithm from Separation Principle for POMDP","display_name":"Belief State Actor-Critic Algorithm from Separation Principle for POMDP","publication_year":2023,"publication_date":"2023-05-31","ids":{"openalex":"https://openalex.org/W4382936420","doi":"https://doi.org/10.23919/acc55779.2023.10155792"},"language":"en","primary_location":{"id":"doi:10.23919/acc55779.2023.10155792","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/acc55779.2023.10155792","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 American Control Conference (ACC)","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/A5101620888","display_name":"Yujie Yang","orcid":"https://orcid.org/0000-0001-7222-0019"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yujie Yang","raw_affiliation_strings":["Tsinghua University,State Key Lab of Automotive Safety and Energy, School of Vehicle and Mobility,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,State Key Lab of Automotive Safety and Energy, School of Vehicle and Mobility,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057254330","display_name":"Yuxuan Jiang","orcid":"https://orcid.org/0000-0003-4285-0495"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxuan Jiang","raw_affiliation_strings":["Tsinghua University,State Key Lab of Automotive Safety and Energy, School of Vehicle and Mobility,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,State Key Lab of Automotive Safety and Energy, School of Vehicle and Mobility,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072222039","display_name":"Jianyu Chen","orcid":"https://orcid.org/0000-0003-0282-8621"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianyu Chen","raw_affiliation_strings":["Tsinghua University,Institute of Interdisciplinary Information Sciences,Beijing,China,100084","Shanghai Qizhi Institute, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Institute of Interdisciplinary Information Sciences,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shanghai Qizhi Institute, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100747108","display_name":"Shengbo Eben Li","orcid":"https://orcid.org/0000-0003-4923-3633"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengbo Eben Li","raw_affiliation_strings":["Tsinghua University,State Key Lab of Automotive Safety and Energy, School of Vehicle and Mobility,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,State Key Lab of Automotive Safety and Energy, School of Vehicle and Mobility,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030950316","display_name":"Ziqing Gu","orcid":"https://orcid.org/0000-0003-2990-9632"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziqing Gu","raw_affiliation_strings":["Tsinghua University,State Key Lab of Automotive Safety and Energy, School of Vehicle and Mobility,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,State Key Lab of Automotive Safety and Energy, School of Vehicle and Mobility,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021699314","display_name":"Yuming Yin","orcid":"https://orcid.org/0000-0002-2854-921X"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuming Yin","raw_affiliation_strings":["Zhejiang University of Technology,College of Mechanical Engineering,Zhejiang,China,310014"],"affiliations":[{"raw_affiliation_string":"Zhejiang University of Technology,College of Mechanical Engineering,Zhejiang,China,310014","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115603610","display_name":"Qian Zhang","orcid":"https://orcid.org/0000-0001-5975-9781"},"institutions":[{"id":"https://openalex.org/I4401726824","display_name":"Horizon Robotics (China)","ror":"https://ror.org/05cmv6g68","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726824"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian Zhang","raw_affiliation_strings":["Horizon Robotics,Beijing,China,100085"],"affiliations":[{"raw_affiliation_string":"Horizon Robotics,Beijing,China,100085","institution_ids":["https://openalex.org/I4401726824"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043098653","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0002-7102-9826"},"institutions":[{"id":"https://openalex.org/I4401726824","display_name":"Horizon Robotics (China)","ror":"https://ror.org/05cmv6g68","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726824"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Yu","raw_affiliation_strings":["Horizon Robotics,Beijing,China,100085"],"affiliations":[{"raw_affiliation_string":"Horizon Robotics,Beijing,China,100085","institution_ids":["https://openalex.org/I4401726824"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5101620888"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.1751,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53660389,"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":"2560","last_page":"2567"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9932000041007996,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9868999719619751,"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/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.927641749382019},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6905555725097656},{"id":"https://openalex.org/keywords/separation-principle","display_name":"Separation principle","score":0.6424033045768738},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6184656620025635},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6097742319107056},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5691332221031189},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.502673864364624},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5008194446563721},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4968288242816925},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4928896427154541},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4205184876918793},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37420833110809326},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.34639984369277954},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3076953887939453},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.26135820150375366},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.21226376295089722},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.12706583738327026}],"concepts":[{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.927641749382019},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6905555725097656},{"id":"https://openalex.org/C62431964","wikidata":"https://www.wikidata.org/wiki/Q2271572","display_name":"Separation principle","level":4,"score":0.6424033045768738},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6184656620025635},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6097742319107056},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5691332221031189},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.502673864364624},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5008194446563721},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4968288242816925},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4928896427154541},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4205184876918793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37420833110809326},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.34639984369277954},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3076953887939453},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.26135820150375366},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.21226376295089722},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.12706583738327026},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C3031470","wikidata":"https://www.wikidata.org/wiki/Q818544","display_name":"State observer","level":3,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc55779.2023.10155792","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/acc55779.2023.10155792","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1484113995","https://openalex.org/W1529558080","https://openalex.org/W1959608418","https://openalex.org/W1994945819","https://openalex.org/W2011418219","https://openalex.org/W2034725503","https://openalex.org/W2038107162","https://openalex.org/W2066505667","https://openalex.org/W2110962519","https://openalex.org/W2124595631","https://openalex.org/W2158907787","https://openalex.org/W2168359464","https://openalex.org/W2171084228","https://openalex.org/W2736601468","https://openalex.org/W2781726626","https://openalex.org/W2890208753","https://openalex.org/W2962854145","https://openalex.org/W2963889160","https://openalex.org/W2995298643","https://openalex.org/W3015082424","https://openalex.org/W3093010610","https://openalex.org/W3195860693","https://openalex.org/W4288294128","https://openalex.org/W4289294484","https://openalex.org/W4362650413","https://openalex.org/W6636732284","https://openalex.org/W6640963894","https://openalex.org/W6678541622","https://openalex.org/W6684973485","https://openalex.org/W6685152286","https://openalex.org/W6711952718","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6751659697","https://openalex.org/W6754184789","https://openalex.org/W6756256016","https://openalex.org/W6765407481","https://openalex.org/W6771217966","https://openalex.org/W6775294054"],"related_works":["https://openalex.org/W2096013579","https://openalex.org/W1589140671","https://openalex.org/W1760611253","https://openalex.org/W52153049","https://openalex.org/W2951545791","https://openalex.org/W1515117609","https://openalex.org/W2294884454","https://openalex.org/W4323315247","https://openalex.org/W3169161914","https://openalex.org/W3208638985"],"abstract_inverted_index":{"Partially":[0],"observable":[1,175],"Markov":[2],"decision":[3,11],"process":[4],"(POMDP)":[5],"is":[6,32,42,154,162],"a":[7,24,72,95,100,124,173],"general":[8,83],"framework":[9],"for":[10,45,80,147],"making":[12],"and":[13,38,90,107,139,159,191,195],"control":[14],"under":[15,86],"uncertainty.":[16],"A":[17],"large":[18],"class":[19],"of":[20,58],"POMDP":[21,84,126],"algorithms":[22],"follows":[23],"two-step":[25,125],"approach,":[26],"in":[27,172],"which":[28,133],"the":[29,35,39,46,50,63,77,113,119,136,148,160,189],"first":[30,134],"step":[31,41],"to":[33,43,75,98,112,145],"estimate":[34],"belief":[36,51,137,152],"state,":[37],"second":[40],"solve":[44,146],"optimal":[47,114,149],"policy":[48,161],"taking":[49],"state":[52,138,153],"as":[53,143],"input.":[54],"The":[55,151],"optimality":[56],"guarantee":[57],"their":[59],"combination":[60],"relies":[61],"on":[62,118],"so-called":[64],"separation":[65,78,120],"principle.":[66],"In":[67],"this":[68],"paper,":[69],"we":[70,122],"propose":[71],"new":[73],"path":[74],"prove":[76,108],"principle":[79],"infinite":[81],"horizon":[82,97],"problems":[85],"both":[87],"discounted":[88],"cost":[89],"average":[91],"cost.":[92],"We":[93,168],"use":[94],"nominal":[96],"split":[99],"virtual":[101],"objective":[102],"function":[103],"into":[104],"two":[105],"parts":[106],"that":[109,182],"it":[110,142],"converges":[111],"state-value":[115],"function.":[116],"Based":[117],"principle,":[121],"design":[123],"algorithm":[127,171,184],"called":[128],"Belief":[129],"State":[130],"Actor-Critic":[131],"(BSAC),":[132],"estimates":[135],"then":[140],"takes":[141],"input":[144],"policy.":[150],"learned":[155,163],"using":[156],"variational":[157],"inference,":[158],"through":[164],"model-based":[165],"reinforcement":[166],"learning.":[167],"test":[169],"our":[170,183],"partially":[174],"multi-lane":[176],"autonomous":[177],"driving":[178,197],"task.":[179],"Results":[180],"show":[181],"achieves":[185],"lower":[186],"costs":[187],"than":[188],"baselines":[190],"learns":[192],"safe,":[193],"efficient,":[194],"smooth":[196],"behaviors.":[198]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}