{"id":"https://openalex.org/W4387678101","doi":"https://doi.org/10.1109/icac57885.2023.10275190","title":"Joint Recurrent Actor-Critic Model for Partially Observable Control","display_name":"Joint Recurrent Actor-Critic Model for Partially Observable Control","publication_year":2023,"publication_date":"2023-08-30","ids":{"openalex":"https://openalex.org/W4387678101","doi":"https://doi.org/10.1109/icac57885.2023.10275190"},"language":"en","primary_location":{"id":"doi:10.1109/icac57885.2023.10275190","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icac57885.2023.10275190","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 28th International Conference on Automation and Computing (ICAC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5106699645","display_name":"Han Xu","orcid":"https://orcid.org/0000-0003-3281-292X"},"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":"Han Xu","raw_affiliation_strings":["Tsinghua University,Department of Automation,Beijing,China","Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101912623","display_name":"Jun Yang","orcid":"https://orcid.org/0000-0002-9386-5825"},"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":"Jun Yang","raw_affiliation_strings":["Tsinghua University,Department of Automation,Beijing,China","Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100644629","display_name":"Bin Liang","orcid":"https://orcid.org/0000-0002-7163-345X"},"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":"Bin Liang","raw_affiliation_strings":["Tsinghua University,Department of Automation,Beijing,China","Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"80","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9739000201225281,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9527999758720398,"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/observability","display_name":"Observability","score":0.7685527801513672},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7674131989479065},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7231481671333313},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6768566966056824},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5496217012405396},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4813005030155182},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.47672954201698303},{"id":"https://openalex.org/keywords/inefficiency","display_name":"Inefficiency","score":0.4597707986831665},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4244527816772461},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.424385666847229},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.42332276701927185},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2557682394981384},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08996284008026123},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08122473955154419}],"concepts":[{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.7685527801513672},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7674131989479065},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7231481671333313},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6768566966056824},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5496217012405396},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4813005030155182},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.47672954201698303},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.4597707986831665},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4244527816772461},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.424385666847229},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.42332276701927185},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2557682394981384},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08996284008026123},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08122473955154419},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icac57885.2023.10275190","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icac57885.2023.10275190","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 28th International Conference on Automation and Computing (ICAC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1555801537","https://openalex.org/W1598140581","https://openalex.org/W2064675550","https://openalex.org/W2091565802","https://openalex.org/W2100677568","https://openalex.org/W2107878631","https://openalex.org/W2108692343","https://openalex.org/W2145014875","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2168359464","https://openalex.org/W2291973609","https://openalex.org/W2746553466","https://openalex.org/W2766447205","https://openalex.org/W2810602713","https://openalex.org/W2890208753","https://openalex.org/W2913668833","https://openalex.org/W2962854145","https://openalex.org/W2963864421","https://openalex.org/W2982316857","https://openalex.org/W2994849131","https://openalex.org/W2996037775","https://openalex.org/W3011120880","https://openalex.org/W3099518626","https://openalex.org/W4214717370","https://openalex.org/W4288294128","https://openalex.org/W6602057636","https://openalex.org/W6638545294","https://openalex.org/W6677939520","https://openalex.org/W6684921986","https://openalex.org/W6696783566","https://openalex.org/W6748839928","https://openalex.org/W6751659697","https://openalex.org/W6754184789","https://openalex.org/W6757184387","https://openalex.org/W6765407481","https://openalex.org/W6771810092","https://openalex.org/W6772005887","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W2046459260","https://openalex.org/W2765830098","https://openalex.org/W2967463586","https://openalex.org/W1971989957","https://openalex.org/W2517338020","https://openalex.org/W3157641275","https://openalex.org/W4312300846","https://openalex.org/W4206221578","https://openalex.org/W11481024","https://openalex.org/W1500110844"],"abstract_inverted_index":{"In":[0,52],"many":[1],"real-world":[2],"robotic":[3],"control":[4,24,159],"tasks,":[5],"limited":[6],"sensors":[7],"with":[8,32,82,100,149],"noise":[9],"could":[10],"affect":[11],"the":[12,78,118,121,124,132,143],"perceptual":[13],"abilities":[14],"of":[15,49,98],"agents.":[16],"Attempts":[17],"to":[18,68,86,106],"solve":[19],"these":[20,70],"partially":[21],"observable":[22],"(PO)":[23],"tasks":[25],"using":[26],"value-based":[27],"deep":[28,60],"reinforcement":[29],"learning":[30],"(RL)":[31],"recurrent":[33,43,65,93],"neural":[34],"networks":[35],"(RNN)":[36],"often":[37],"suffer":[38],"from":[39],"two":[40,71],"prominent":[41],"problems:":[42],"update":[44],"inefficiency":[45],"and":[46,123,130,152],"overestimation":[47],"bias":[48],"value":[50],"approximation.":[51],"this":[53],"paper,":[54],"we":[55],"propose":[56],"an":[57,83],"off-policy":[58],"model-free":[59],"RL":[61],"algorithm,":[62],"named":[63],"joint":[64,113],"actor-critic":[66,114],"(JRAC),":[67],"tackle":[69],"problems":[72],"simultaneously.":[73],"First,":[74],"our":[75],"algorithm":[76,145],"develops":[77],"stored":[79],"encoded":[80],"state":[81],"episode":[84],"mask":[85],"implement":[87],"step-based":[88],"experience":[89],"replay":[90],"for":[91,120],"efficient":[92],"update.":[94],"Then":[95],"a":[96,112],"pair":[97],"critics":[99],"independent":[101],"LSTM":[102],"parts":[103],"is":[104],"introduced":[105],"reduce":[107],"overestimation.":[108],"We":[109],"further":[110],"design":[111],"architecture":[115],"by":[116],"sharing":[117],"RNN":[119],"actor":[122],"critic,":[125],"which":[126],"improves":[127],"computational":[128],"efficiency":[129],"accelerates":[131],"training":[133],"process":[134],"without":[135],"causing":[136],"intolerable":[137],"instabilities.":[138],"Our":[139],"experiments":[140],"show":[141],"that":[142],"proposed":[144],"can":[146],"effectively":[147],"deal":[148],"partial":[150],"observability":[151],"performs":[153],"well":[154],"on":[155],"several":[156],"complicated":[157],"PO":[158],"tasks.":[160]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}