{"id":"https://openalex.org/W3188263527","doi":"https://doi.org/10.24963/ijcai.2021/71","title":"Data-Efficient Reinforcement Learning for Malaria Control","display_name":"Data-Efficient Reinforcement Learning for Malaria Control","publication_year":2021,"publication_date":"2021-08-01","ids":{"openalex":"https://openalex.org/W3188263527","doi":"https://doi.org/10.24963/ijcai.2021/71","mag":"3188263527"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2021/71","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/71","pdf_url":"https://www.ijcai.org/proceedings/2021/0071.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2021/0071.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089307887","display_name":"Lixin Zou","orcid":"https://orcid.org/0000-0001-6755-871X"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lixin Zou","raw_affiliation_strings":["Baidu Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc","institution_ids":["https://openalex.org/I98301712"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5089307887"],"corresponding_institution_ids":["https://openalex.org/I98301712"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.12908899,"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":"507","last_page":"513"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980999827384949,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9979000091552734,"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":0.784929633140564},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7684038877487183},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5958030819892883},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5773382782936096},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5738001465797424},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5222887992858887},{"id":"https://openalex.org/keywords/scratch","display_name":"Scratch","score":0.5198029279708862},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4829375147819519},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.4379047155380249},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.4347071051597595},{"id":"https://openalex.org/keywords/competition","display_name":"Competition (biology)","score":0.4227112829685211},{"id":"https://openalex.org/keywords/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.4193708896636963},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.2888248562812805},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.23264965415000916},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10765644907951355}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.784929633140564},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7684038877487183},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5958030819892883},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5773382782936096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5738001465797424},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5222887992858887},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.5198029279708862},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4829375147819519},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4379047155380249},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.4347071051597595},{"id":"https://openalex.org/C91306197","wikidata":"https://www.wikidata.org/wiki/Q45767","display_name":"Competition (biology)","level":2,"score":0.4227112829685211},{"id":"https://openalex.org/C46149586","wikidata":"https://www.wikidata.org/wiki/Q11785332","display_name":"Monte Carlo tree search","level":3,"score":0.4193708896636963},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.2888248562812805},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.23264965415000916},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10765644907951355},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"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:10.24963/ijcai.2021/71","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/71","pdf_url":"https://www.ijcai.org/proceedings/2021/0071.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2021/71","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/71","pdf_url":"https://www.ijcai.org/proceedings/2021/0071.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","score":0.6100000143051147,"display_name":"Good health and well-being"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3188263527.pdf","grobid_xml":"https://content.openalex.org/works/W3188263527.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1596778849","https://openalex.org/W1747856733","https://openalex.org/W1975779216","https://openalex.org/W2058775476","https://openalex.org/W2100752967","https://openalex.org/W2103988429","https://openalex.org/W2108738385","https://openalex.org/W2115876816","https://openalex.org/W2123447947","https://openalex.org/W2123859855","https://openalex.org/W2124352385","https://openalex.org/W2140135625","https://openalex.org/W2155027007","https://openalex.org/W2155836220","https://openalex.org/W2224767274","https://openalex.org/W2488247662","https://openalex.org/W2549617326","https://openalex.org/W2700407638","https://openalex.org/W2766447205","https://openalex.org/W2890208753","https://openalex.org/W2963842088","https://openalex.org/W2964125642","https://openalex.org/W3040127368","https://openalex.org/W3124229194","https://openalex.org/W4211049957","https://openalex.org/W4298857966"],"related_works":["https://openalex.org/W2475116013","https://openalex.org/W2770018148","https://openalex.org/W2358308169","https://openalex.org/W2385135707","https://openalex.org/W2140315382","https://openalex.org/W2059109728","https://openalex.org/W322691623","https://openalex.org/W2494989134","https://openalex.org/W2509444723","https://openalex.org/W3136325136"],"abstract_inverted_index":{"Sequential":[0],"decision-making":[1],"under":[2],"cost-sensitive":[3],"tasks":[4],"is":[5,33,85,147],"prohibitively":[6],"daunting,":[7],"especially":[8],"for":[9],"the":[10,83,102,106,117,120,123,126,139,167,170],"problem":[11],"that":[12,145],"has":[13],"a":[14,36,43,47,53,79,86,112,154],"significant":[15],"impact":[16],"on":[17,153,169],"people's":[18],"daily":[19],"lives,":[20],"such":[21],"as":[22],"malaria":[23,172],"control,":[24],"treatment":[25],"recommendation.":[26],"The":[27],"main":[28],"challenge":[29],"faced":[30],"by":[31,40],"policymakers":[32],"to":[34,100,115,125],"learn":[35],"policy":[37,56],"from":[38,75],"scratch":[39,76],"interacting":[41],"with":[42,68,128],"complex":[44],"environment":[45],"in":[46,77,132],"few":[48,80],"trials.":[49,81],"This":[50],"work":[51],"introduces":[52],"practical,":[54],"data-efficient":[55],"learning":[57,74,89],"method,":[58],"named":[59],"Variance-Bonus":[60],"Monte":[61],"Carlo":[62],"Tree":[63],"Search~(VB-MCTS),":[64],"which":[65],"can":[66,130],"copy":[67],"very":[69],"little":[70],"data":[71],"and":[72,135,159],"facilitate":[73],"only":[78],"Specifically,":[82],"solution":[84],"model-based":[87],"reinforcement":[88],"method.":[90],"To":[91],"avoid":[92],"model":[93],"bias,":[94],"we":[95,110],"apply":[96],"Gaussian":[97],"Process~(GP)":[98],"regression":[99],"estimate":[101],"transitions":[103],"explicitly.":[104],"With":[105],"GP":[107],"world":[108],"model,":[109],"propose":[111],"variance-bonus":[113],"reward":[114,124],"measure":[116],"uncertainty":[118],"about":[119],"world.":[121],"Adding":[122],"planning":[127],"MCTS":[129],"result":[131],"more":[133],"efficient":[134],"effective":[136],"exploration.":[137],"Furthermore,":[138],"derived":[140],"polynomial":[141],"sample":[142,148],"complexity":[143],"indicates":[144],"VB-MCTS":[146],"efficient.":[149],"Finally,":[150],"outstanding":[151],"performance":[152],"competitive":[155],"world-level":[156],"RL":[157],"competition":[158],"extensive":[160],"experimental":[161],"results":[162],"verify":[163],"its":[164],"advantage":[165],"over":[166],"state-of-the-art":[168],"challenging":[171],"control":[173],"task.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}