{"id":"https://openalex.org/W4400581349","doi":"https://doi.org/10.1142/s1793351x2444001x","title":"Human-Inspired Meta-Reinforcement Learning Using Bayesian Knowledge and Enhanced Deep Q-Network","display_name":"Human-Inspired Meta-Reinforcement Learning Using Bayesian Knowledge and Enhanced Deep Q-Network","publication_year":2024,"publication_date":"2024-07-12","ids":{"openalex":"https://openalex.org/W4400581349","doi":"https://doi.org/10.1142/s1793351x2444001x"},"language":"en","primary_location":{"id":"doi:10.1142/s1793351x2444001x","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1142/s1793351x2444001x","pdf_url":null,"source":{"id":"https://openalex.org/S4210201727","display_name":"International Journal of Semantic Computing","issn_l":"1793-351X","issn":["1793-351X","1793-7108"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Semantic Computing","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/A5113931831","display_name":"Joshua Ho","orcid":"https://orcid.org/0000-0002-7165-1893"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]},{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]},{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Joshua Ho","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, 128 Academia Road, Section 2, Nankang, Taipei 115, Taiwan","Institute of Information Systems and Applications, National Tsing Hua University, Hsinchu, Taiwan","TIGP SNHCC, Academia Sinica, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-7165-1893","affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, 128 Academia Road, Section 2, Nankang, Taipei 115, Taiwan","institution_ids":["https://openalex.org/I4210098366"]},{"raw_affiliation_string":"Institute of Information Systems and Applications, National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"TIGP SNHCC, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076583461","display_name":"Chien\u2010Min Wang","orcid":"https://orcid.org/0000-0002-2992-9898"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]},{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chien-Min Wang","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, 128 Academia Road, Section 2, Nankang, Taipei 115, Taiwan","TIGP SNHCC, Academia Sinica, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-2992-9898","affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, 128 Academia Road, Section 2, Nankang, Taipei 115, Taiwan","institution_ids":["https://openalex.org/I4210098366"]},{"raw_affiliation_string":"TIGP SNHCC, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057871439","display_name":"Chung\u2010Ta King","orcid":"https://orcid.org/0000-0002-5041-5795"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]},{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chung-Ta King","raw_affiliation_strings":["Department of Computer Science, National Tsing Hua University, 101, Section 2, Kuang-Fu Road, Hsinchu 300044, Taiwan","Institute of Information Systems and Applications, National Tsing Hua University, Hsinchu, Taiwan","TIGP SNHCC, Academia Sinica, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-5041-5795","affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Tsing Hua University, 101, Section 2, Kuang-Fu Road, Hsinchu 300044, Taiwan","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"Institute of Information Systems and Applications, National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"TIGP SNHCC, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114190404","display_name":"Yi-Hsin You","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]},{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Hsin You","raw_affiliation_strings":["Department of Computer Science, National Taiwan University, No. 1, Sec. 4, Roosevelt Rd., Taipei, 106319, Taiwan","Institute of Information Science, Academia Sinica, 128 Academia Road, Section 2, Nankang, Taipei 115, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Taiwan University, No. 1, Sec. 4, Roosevelt Rd., Taipei, 106319, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, 128 Academia Road, Section 2, Nankang, Taipei 115, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011866841","display_name":"Chi-Wei Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]},{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chi-Wei Feng","raw_affiliation_strings":["Department of Computer Science, National Tsing Hua University, 101, Section 2, Kuang-Fu Road, Hsinchu 300044, Taiwan","Institute of Information Science, Academia Sinica, 128 Academia Road, Section 2, Nankang, Taipei 115, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Tsing Hua University, 101, Section 2, Kuang-Fu Road, Hsinchu 300044, Taiwan","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, 128 Academia Road, Section 2, Nankang, Taipei 115, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5113931831"],"corresponding_institution_ids":["https://openalex.org/I25846049","https://openalex.org/I4210098366","https://openalex.org/I84653119"],"apc_list":null,"apc_paid":null,"fwci":0.3147,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.62925623,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"18","issue":"04","first_page":"547","last_page":"569"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.5946000218391418,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.5946000218391418,"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/computer-science","display_name":"Computer science","score":0.8478962182998657},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8320163488388062},{"id":"https://openalex.org/keywords/bayesian-network","display_name":"Bayesian network","score":0.6638675332069397},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6526241898536682},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5130218863487244},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4357859194278717}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8478962182998657},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8320163488388062},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.6638675332069397},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6526241898536682},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5130218863487244},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4357859194278717}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s1793351x2444001x","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1142/s1793351x2444001x","pdf_url":null,"source":{"id":"https://openalex.org/S4210201727","display_name":"International Journal of Semantic Computing","issn_l":"1793-351X","issn":["1793-351X","1793-7108"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Semantic Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1918878574","https://openalex.org/W2143117649","https://openalex.org/W2143891888","https://openalex.org/W2145339207","https://openalex.org/W2197227940","https://openalex.org/W2236244207","https://openalex.org/W2469622991","https://openalex.org/W2612690371","https://openalex.org/W2746553466","https://openalex.org/W2761873684","https://openalex.org/W2916904544","https://openalex.org/W2942444880","https://openalex.org/W2944766483","https://openalex.org/W2966576392","https://openalex.org/W2997289589","https://openalex.org/W3039651739","https://openalex.org/W3132496089","https://openalex.org/W3137292195","https://openalex.org/W3146546164","https://openalex.org/W3150811281","https://openalex.org/W3164005523","https://openalex.org/W3210036045","https://openalex.org/W4233881498","https://openalex.org/W4307651293","https://openalex.org/W4312036125"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Over":[0],"the":[1,36,91,98,104,117,123,136,147,178,210],"last":[2],"decades,":[3],"there":[4],"has":[5],"been":[6],"growing":[7],"interest":[8],"in":[9,11,209],"research":[10,38],"multiple":[12],"and":[13,25,66,78,106,121,184,198,204],"interdisciplinary":[14],"fields":[15],"of":[16,108],"human-AI":[17],"computing.":[18],"In":[19,51,144],"particular,":[20],"approaches":[21,49],"integrating":[22,187],"human\u2019s":[23],"perspective":[24],"design":[26],"with":[27,141],"reinforcement":[28],"learning":[29,60,142,159,192],"(RL)":[30],"have":[31,151],"received":[32],"more":[33,167,193,205],"attention.":[34],"However,":[35],"current":[37],"on":[39,56,103,158],"RL":[40],"may":[41],"need":[42],"to":[43,63,69,96,146,175,196,201],"consider":[44],"its":[45],"enhancement":[46],"from":[47,125],"human-inspired":[48,86,188],"further.":[50],"this":[52],"work,":[53],"we":[54,89,150,182],"focus":[55],"enabling":[57],"a":[58,82,109,161],"meta-reinforcement":[59],"(meta-RL)":[61],"agent":[62,92,118,124,137],"achieve":[64],"adaptation":[65],"generalization,":[67],"according":[68],"modeling":[70],"Markov":[71],"Decision":[72],"Processes":[73],"(MDP)":[74],"using":[75],"Bayesian":[76,110],"knowledge":[77,105],"analysis.":[79,111],"By":[80],"introducing":[81],"novel":[83],"framework":[84,114],"called":[85],"meta-RL":[87,189],"(HMRL),":[88],"incorporate":[90],"performing":[93],"resilient":[94],"actions":[95],"leverage":[97],"dynamic":[99],"dense":[100],"reward":[101],"based":[102,157],"prediction":[107],"The":[112,128],"proposed":[113],"can":[115,190],"make":[116],"learn":[119],"generalization":[120],"prevent":[122],"failing":[126],"catastrophically.":[127],"experimental":[129],"results":[130],"show":[131],"that":[132,186],"our":[133],"approach":[134],"helps":[135],"reduce":[138],"computational":[139],"costs":[140],"adaptation.":[143],"addition":[145],"system":[148],"design,":[149],"also":[152],"extended":[153],"further":[154],"algorithmic":[155],"improvement":[156],"within":[160],"deep":[162],"Q-network":[163],"(DQN)":[164],"implementations":[165],"for":[166],"complicated":[168],"future":[169],"tasks,":[170],"which":[171],"compared":[172],"replay":[173],"buffers":[174],"possibly":[176],"enhance":[177],"optimization":[179],"process.":[180],"Finally,":[181],"conclude":[183],"anticipate":[185],"enable":[191],"formulations":[194],"relating":[195],"robustness":[197],"scalability,":[199],"leading":[200],"promising":[202],"directions":[203],"complex":[206],"AI":[207],"goals":[208],"future.":[211]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}