{"id":"https://openalex.org/W2997881821","doi":"https://doi.org/10.1177/1059712319891641","title":"Constrained representation learning for recurrent policy optimisation under uncertainty","display_name":"Constrained representation learning for recurrent policy optimisation under uncertainty","publication_year":2019,"publication_date":"2019-12-30","ids":{"openalex":"https://openalex.org/W2997881821","doi":"https://doi.org/10.1177/1059712319891641","mag":"2997881821"},"language":"en","primary_location":{"id":"doi:10.1177/1059712319891641","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1059712319891641","pdf_url":null,"source":{"id":"https://openalex.org/S183337005","display_name":"Adaptive Behavior","issn_l":"1059-7123","issn":["1059-7123","1741-2633"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adaptive Behavior","raw_type":"journal-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/A5020334464","display_name":"Viet-Hung Dang","orcid":null},"institutions":[{"id":"https://openalex.org/I170238339","display_name":"Duy Tan University","ror":"https://ror.org/05ezss144","country_code":"VN","type":"education","lineage":["https://openalex.org/I170238339"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Viet-Hung Dang","raw_affiliation_strings":["Institute of Research and Development, DuyTan University, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Research and Development, DuyTan University, Vietnam","institution_ids":["https://openalex.org/I170238339"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043775193","display_name":"Ngo Anh Vien","orcid":"https://orcid.org/0000-0001-9646-267X"},"institutions":[{"id":"https://openalex.org/I126231945","display_name":"Queen's University Belfast","ror":"https://ror.org/00hswnk62","country_code":"GB","type":"education","lineage":["https://openalex.org/I126231945"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ngo Anh Vien","raw_affiliation_strings":["School of EEECS, Queen\u2019s University Belfast, UK","School of EEECS, Queen's University Belfast, UK"],"raw_orcid":"https://orcid.org/0000-0001-9646-267X","affiliations":[{"raw_affiliation_string":"School of EEECS, Queen\u2019s University Belfast, UK","institution_ids":["https://openalex.org/I126231945"]},{"raw_affiliation_string":"School of EEECS, Queen's University Belfast, UK","institution_ids":["https://openalex.org/I126231945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112330829","display_name":"TaeChoong Chung","orcid":null},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"TaeChoong Chung","raw_affiliation_strings":["Artificial Intelligent Lab, Department of Computer Engineering, Kyung Hee University, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligent Lab, Department of Computer Engineering, Kyung Hee University, Korea","institution_ids":["https://openalex.org/I35928602"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5112330829"],"corresponding_institution_ids":["https://openalex.org/I35928602"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17472512,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"29","issue":"3","first_page":"253","last_page":"265"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9915000200271606,"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":0.9915000200271606,"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":0.989799976348877,"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/T10409","display_name":"Fuel Cells and Related Materials","score":0.982699990272522,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/computer-science","display_name":"Computer science","score":0.7833187580108643},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.7485913038253784},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5788413882255554},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5755420923233032},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.544023871421814},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5327292680740356},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5240448117256165},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5092610120773315},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46719691157341003},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4571854770183563},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.44684356451034546},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.4394318461418152},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43531349301338196},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.32105594873428345},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23710224032402039},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.18659695982933044},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.1381843090057373},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09360846877098083},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.06605228781700134}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7833187580108643},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.7485913038253784},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5788413882255554},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5755420923233032},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.544023871421814},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5327292680740356},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5240448117256165},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5092610120773315},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46719691157341003},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4571854770183563},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.44684356451034546},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.4394318461418152},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43531349301338196},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.32105594873428345},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23710224032402039},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.18659695982933044},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.1381843090057373},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09360846877098083},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.06605228781700134},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1177/1059712319891641","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1059712319891641","pdf_url":null,"source":{"id":"https://openalex.org/S183337005","display_name":"Adaptive Behavior","issn_l":"1059-7123","issn":["1059-7123","1741-2633"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adaptive Behavior","raw_type":"journal-article"},{"id":"pmh:oai:pure.qub.ac.uk/portal:publications/521ad319-613e-43c9-a291-8d6a9c0dec01","is_oa":false,"landing_page_url":"https://pure.qub.ac.uk/en/publications/521ad319-613e-43c9-a291-8d6a9c0dec01","pdf_url":null,"source":{"id":"https://openalex.org/S4306402319","display_name":"Research Portal (Queen's University Belfast)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I126231945","host_organization_name":"Queen's University Belfast","host_organization_lineage":["https://openalex.org/I126231945"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Dang , V H , Vien , N A & Chung , T C 2019 , ' Constrained representation learning for recurrent policy optimisation under uncertainty ' , Adaptive Behavior . https://doi.org/10.1177/1059712319891641","raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309617","display_name":"National Foundation for Science and Technology Development","ror":"https://ror.org/04rw64z44"},{"id":"https://openalex.org/F4320320006","display_name":"Royal Society","ror":"https://ror.org/03wnrjx87"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W128438430","https://openalex.org/W398859631","https://openalex.org/W1484113995","https://openalex.org/W1498436455","https://openalex.org/W1570690983","https://openalex.org/W2022737303","https://openalex.org/W2034725503","https://openalex.org/W2052259295","https://openalex.org/W2064675550","https://openalex.org/W2077933344","https://openalex.org/W2103581399","https://openalex.org/W2119717200","https://openalex.org/W2125838338","https://openalex.org/W2141690016","https://openalex.org/W2143256202","https://openalex.org/W2144446635","https://openalex.org/W2145339207","https://openalex.org/W2150355110","https://openalex.org/W2154997814","https://openalex.org/W2157331557","https://openalex.org/W2168359464","https://openalex.org/W2252143850","https://openalex.org/W2346626577","https://openalex.org/W2560674852","https://openalex.org/W2574572704","https://openalex.org/W2592249290","https://openalex.org/W2595840341","https://openalex.org/W2604799680","https://openalex.org/W2613433911","https://openalex.org/W2734777338","https://openalex.org/W2766736793","https://openalex.org/W2802349643","https://openalex.org/W2978329087","https://openalex.org/W3103182070","https://openalex.org/W4299828299","https://openalex.org/W4365799834"],"related_works":["https://openalex.org/W2096013579","https://openalex.org/W1760611253","https://openalex.org/W52153049","https://openalex.org/W1589140671","https://openalex.org/W2951545791","https://openalex.org/W1515117609","https://openalex.org/W2294884454","https://openalex.org/W4323315247","https://openalex.org/W3169161914","https://openalex.org/W4321379664"],"abstract_inverted_index":{"Learning":[0],"to":[1,36,81,100,178,203,228],"make":[2],"decisions":[3],"in":[4,41],"partially":[5,47],"observable":[6,48],"environments":[7],"is":[8],"a":[9,14,27,31,46,109,116,157,190],"notorious":[10],"problem":[11,213],"that":[12,73,149],"requires":[13],"complex":[15,232],"representation":[16,86,117,194,217,222],"of":[17,33,60,111,118,156,221,238],"controllers.":[18],"In":[19,64],"most":[20],"work,":[21],"the":[22,58,76,102,131,154,162,171,176,186,210,236],"controllers":[23],"are":[24],"designed":[25],"as":[26,45,113],"non-linear":[28,191],"mapping":[29],"from":[30],"sequence":[32,135],"temporal":[34],"observations":[35,89,112],"actions.":[37],"These":[38],"problems":[39],"can,":[40],"principle,":[42],"be":[43,55],"formulated":[44],"Markov":[49],"decision":[50],"process":[51],"whose":[52],"policy":[53,98,163,204,211,225,239],"can":[54,124],"parameterised":[56],"through":[57],"use":[59],"recurrent":[61,97],"neural":[62],"networks.":[63],"this":[65],"paper,":[66],"we":[67],"will":[68,150,206],"propose":[69],"an":[70,83,147],"alternative":[71,127],"framework":[72,80],"(a)":[74],"uses":[75],"Long-Short-Term-Memory":[77],"(LSTM)":[78],"Encoder-Decoder":[79],"learn":[82,230],"internal":[84,119,159,173],"state":[85,160,174,193,216],"for":[87,161],"historical":[88],"and":[90,152,214,224,234],"then":[91],"(b)":[92],"integrates":[93],"it":[94],"into":[95,115],"existing":[96],"models":[99],"improve":[101,235],"task":[103],"performance.":[104],"The":[105,121,141,166,219],"LSTM":[106,122],"Encoder":[107],"encodes":[108],"history":[110],"input":[114,133],"states.":[120],"Decoder":[123],"perform":[125],"two":[126],"decoding":[128,198],"tasks:":[129],"predicting":[130,137],"same":[132],"observation":[134,139,181],"or":[136],"future":[138,180],"sequences.":[140,182],"first":[142],"proposed":[143,168],"decoder":[144,169],"acts":[145],"like":[146,189],"auto-encoder":[148],"guide":[151,208],"constrain":[153],"learning":[155,223,240],"useful":[158],"optimisation":[164,212,226],"task.":[165],"second":[167],"decodes":[170],"learnt":[172],"by":[175],"encoder":[177],"predict":[179],"This":[183],"idea":[184],"makes":[185],"network":[187],"act":[188],"predictive":[192],"model.":[195],"Both":[196],"these":[197],"parts,":[199],"which":[200],"introduce":[201],"constraints":[202],"representation,":[205],"help":[207,229],"both":[209],"latent":[215],"learning.":[218],"integration":[220],"aims":[227],"more":[231],"policies":[233],"performance":[237],"tasks.":[241]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}