{"id":"https://openalex.org/W2794134065","doi":"https://doi.org/10.1109/iww-bci.2018.8311512","title":"Context-dependent meta-control for reinforcement learning using a Dirichlet process Gaussian mixture model","display_name":"Context-dependent meta-control for reinforcement learning using a Dirichlet process Gaussian mixture model","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2794134065","doi":"https://doi.org/10.1109/iww-bci.2018.8311512","mag":"2794134065"},"language":"en","primary_location":{"id":"doi:10.1109/iww-bci.2018.8311512","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iww-bci.2018.8311512","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 6th International Conference on Brain-Computer Interface (BCI)","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/A5031735933","display_name":"Dongjae Kim","orcid":"https://orcid.org/0000-0002-4513-9087"},"institutions":[{"id":"https://openalex.org/I4210101891","display_name":"Korea Institute of Brain Science","ror":"https://ror.org/017stnw60","country_code":"KR","type":"facility","lineage":["https://openalex.org/I4210101891"]},{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Dongjae Kim","raw_affiliation_strings":["Department of bio and brain engineering, Korea Advanced Institute of Science and Technology, Daejeon, Korea"],"affiliations":[{"raw_affiliation_string":"Department of bio and brain engineering, Korea Advanced Institute of Science and Technology, Daejeon, Korea","institution_ids":["https://openalex.org/I4210101891","https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075631319","display_name":"Sang Wan Lee","orcid":"https://orcid.org/0000-0001-6266-9613"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I4210101891","display_name":"Korea Institute of Brain Science","ror":"https://ror.org/017stnw60","country_code":"KR","type":"facility","lineage":["https://openalex.org/I4210101891"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sang Wan Lee","raw_affiliation_strings":["Department of bio and brain engineering, Korea Advanced Institute of Science and Technology, Daejeon, Korea"],"affiliations":[{"raw_affiliation_string":"Department of bio and brain engineering, Korea Advanced Institute of Science and Technology, Daejeon, Korea","institution_ids":["https://openalex.org/I4210101891","https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5031735933"],"corresponding_institution_ids":["https://openalex.org/I157485424","https://openalex.org/I4210101891"],"apc_list":null,"apc_paid":null,"fwci":0.3679,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.58181849,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11236","display_name":"Control Systems and Identification","score":0.9650999903678894,"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/T11236","display_name":"Control Systems and Identification","score":0.9650999903678894,"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"}},{"id":"https://openalex.org/T10621","display_name":"Gene Regulatory Network Analysis","score":0.9556000232696533,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9384999871253967,"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":0.9063428640365601},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7623998522758484},{"id":"https://openalex.org/keywords/arbitration","display_name":"Arbitration","score":0.6812869310379028},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6384199857711792},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5726158618927002},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.564123809337616},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.5119072198867798},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47595712542533875},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4430113434791565},{"id":"https://openalex.org/keywords/dirichlet-process","display_name":"Dirichlet process","score":0.4318258762359619},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.41947075724601746},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4136943519115448},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.29356706142425537}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9063428640365601},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7623998522758484},{"id":"https://openalex.org/C160151201","wikidata":"https://www.wikidata.org/wiki/Q207946","display_name":"Arbitration","level":2,"score":0.6812869310379028},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6384199857711792},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5726158618927002},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.564123809337616},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.5119072198867798},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47595712542533875},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4430113434791565},{"id":"https://openalex.org/C2781280628","wikidata":"https://www.wikidata.org/wiki/Q5280766","display_name":"Dirichlet process","level":3,"score":0.4318258762359619},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.41947075724601746},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4136943519115448},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.29356706142425537},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iww-bci.2018.8311512","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iww-bci.2018.8311512","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 6th International Conference on Brain-Computer Interface (BCI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5799999833106995,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2120636621","https://openalex.org/W2129299900","https://openalex.org/W2135173838","https://openalex.org/W2156737235","https://openalex.org/W2167362547","https://openalex.org/W2168277610","https://openalex.org/W3145269374","https://openalex.org/W4254499902","https://openalex.org/W6678007500","https://openalex.org/W6683195989"],"related_works":["https://openalex.org/W3095478977","https://openalex.org/W2388352914","https://openalex.org/W2914422975","https://openalex.org/W1992917560","https://openalex.org/W2351937989","https://openalex.org/W2112428735","https://openalex.org/W2378516794","https://openalex.org/W2347397841","https://openalex.org/W2381910504","https://openalex.org/W2379487193"],"abstract_inverted_index":{"Arbitration":[0],"between":[1],"model-based":[2,95],"(MB)":[3],"and":[4,97],"model-free":[5,93],"(MF)":[6],"reinforcement":[7,15,29],"learning":[8,30],"(RL)":[9],"is":[10],"key":[11],"feature":[12],"of":[13,20,34,52,83],"human":[14],"learning.":[16,58],"The":[17,85],"computational":[18],"model":[19,66,87],"arbitration":[21,45,69,98],"control":[22],"has":[23],"been":[24],"demonstrated":[25],"to":[26,80],"outperform":[27],"conventional":[28,92],"algorithm,":[31],"in":[32,55],"terms":[33],"not":[35,48],"only":[36],"behavioral":[37],"data":[38],"but":[39],"also":[40],"neural":[41],"signals.":[42],"However,":[43],"this":[44],"process":[46,63],"does":[47],"take":[49],"full":[50],"account":[51],"contextual":[53,81],"changes":[54,82],"environment":[56],"during":[57],"By":[59],"incorporating":[60],"a":[61,73,91],"Dirichlet":[62],"Gaussian":[64],"mixture":[65],"into":[67],"the":[68],"process,":[70],"we":[71],"propose":[72],"meta-controller":[74],"for":[75],"RL":[76],"that":[77],"quickly":[78],"adapts":[79],"environment.":[84],"proposed":[86],"performs":[88],"better":[89],"than":[90],"RL,":[94,96],"model.":[99]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}