{"id":"https://openalex.org/W2957466728","doi":"https://doi.org/10.2478/amcs-2019-0026","title":"An Active Exploration Method for Data Efficient Reinforcement Learning","display_name":"An Active Exploration Method for Data Efficient Reinforcement Learning","publication_year":2019,"publication_date":"2019-06-01","ids":{"openalex":"https://openalex.org/W2957466728","doi":"https://doi.org/10.2478/amcs-2019-0026","mag":"2957466728"},"language":"en","primary_location":{"id":"doi:10.2478/amcs-2019-0026","is_oa":true,"landing_page_url":"https://doi.org/10.2478/amcs-2019-0026","pdf_url":"https://content.sciendo.com/downloadpdf/journals/amcs/29/2/article-p351.pdf","source":{"id":"https://openalex.org/S117679522","display_name":"International Journal of Applied Mathematics and Computer Science","issn_l":"1641-876X","issn":["1641-876X","2083-8492"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320322","host_organization_name":"De Gruyter Open","host_organization_lineage":["https://openalex.org/P4310320322","https://openalex.org/P4310313990"],"host_organization_lineage_names":["De Gruyter Open","De Gruyter"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Applied Mathematics and Computer Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://content.sciendo.com/downloadpdf/journals/amcs/29/2/article-p351.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102793120","display_name":"Dongfang Zhao","orcid":"https://orcid.org/0000-0001-6110-9219"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongfang Zhao","raw_affiliation_strings":["School of Computer Science and Technology , Harbin Institute of Technology , West Dazhi Street #92, Harbin 150001 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology , Harbin Institute of Technology , West Dazhi Street #92, Harbin 150001 , China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101726410","display_name":"Jiafeng Liu","orcid":"https://orcid.org/0009-0005-5530-8744"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiafeng Liu","raw_affiliation_strings":["School of Computer Science and Technology , Harbin Institute of Technology , West Dazhi Street #92, Harbin 150001 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology , Harbin Institute of Technology , West Dazhi Street #92, Harbin 150001 , China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100449415","display_name":"Rui Wu","orcid":"https://orcid.org/0000-0003-0941-2688"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Wu","raw_affiliation_strings":["School of Computer Science and Technology , Harbin Institute of Technology , West Dazhi Street #92, Harbin 150001 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology , Harbin Institute of Technology , West Dazhi Street #92, Harbin 150001 , China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101019778","display_name":"Dansong Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dansong Cheng","raw_affiliation_strings":["School of Computer Science and Technology , Harbin Institute of Technology , West Dazhi Street #92, Harbin 150001 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology , Harbin Institute of Technology , West Dazhi Street #92, Harbin 150001 , China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100873220","display_name":"Xianglong Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianglong Tang","raw_affiliation_strings":["School of Computer Science and Technology , Harbin Institute of Technology , West Dazhi Street #92, Harbin 150001 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology , Harbin Institute of Technology , West Dazhi Street #92, Harbin 150001 , China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5101019778"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":{"value":4080,"currency":"PLN","value_usd":1100},"apc_paid":{"value":4080,"currency":"PLN","value_usd":1100},"fwci":0.4236,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.7058604,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"29","issue":"2","first_page":"351","last_page":"362"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9962000250816345,"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":0.9962000250816345,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9830999970436096,"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"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9758999943733215,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7575253844261169},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7315571904182434},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4891257882118225},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4732537865638733},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.46830713748931885},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4538595974445343},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.44477295875549316},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.4256141185760498},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.41739070415496826},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.3611385226249695},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32382261753082275}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7575253844261169},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7315571904182434},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4891257882118225},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4732537865638733},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.46830713748931885},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4538595974445343},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.44477295875549316},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.4256141185760498},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.41739070415496826},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3611385226249695},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32382261753082275},{"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":2,"locations":[{"id":"doi:10.2478/amcs-2019-0026","is_oa":true,"landing_page_url":"https://doi.org/10.2478/amcs-2019-0026","pdf_url":"https://content.sciendo.com/downloadpdf/journals/amcs/29/2/article-p351.pdf","source":{"id":"https://openalex.org/S117679522","display_name":"International Journal of Applied Mathematics and Computer Science","issn_l":"1641-876X","issn":["1641-876X","2083-8492"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320322","host_organization_name":"De Gruyter Open","host_organization_lineage":["https://openalex.org/P4310320322","https://openalex.org/P4310313990"],"host_organization_lineage_names":["De Gruyter Open","De Gruyter"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Applied Mathematics and Computer Science","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:f6dc2b7911544c01b01453a6d6a5e207","is_oa":false,"landing_page_url":"https://doaj.org/article/f6dc2b7911544c01b01453a6d6a5e207","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Journal of Applied Mathematics and Computer Science, Vol 29, Iss 2, Pp 351-362 (2019)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.2478/amcs-2019-0026","is_oa":true,"landing_page_url":"https://doi.org/10.2478/amcs-2019-0026","pdf_url":"https://content.sciendo.com/downloadpdf/journals/amcs/29/2/article-p351.pdf","source":{"id":"https://openalex.org/S117679522","display_name":"International Journal of Applied Mathematics and Computer Science","issn_l":"1641-876X","issn":["1641-876X","2083-8492"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320322","host_organization_name":"De Gruyter Open","host_organization_lineage":["https://openalex.org/P4310320322","https://openalex.org/P4310313990"],"host_organization_lineage_names":["De Gruyter Open","De Gruyter"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Applied Mathematics and Computer Science","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2957466728.pdf","grobid_xml":"https://content.openalex.org/works/W2957466728.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1949804828","https://openalex.org/W1980035368","https://openalex.org/W2000191307","https://openalex.org/W2018705428","https://openalex.org/W2097113539","https://openalex.org/W2097778153","https://openalex.org/W2100677568","https://openalex.org/W2130105540","https://openalex.org/W2130913800","https://openalex.org/W2140135625","https://openalex.org/W2158641818","https://openalex.org/W2528489519","https://openalex.org/W2612610049","https://openalex.org/W2765349170","https://openalex.org/W2949368738","https://openalex.org/W2951948137","https://openalex.org/W2962872206","https://openalex.org/W2963634205","https://openalex.org/W2964161785","https://openalex.org/W3041202696"],"related_works":["https://openalex.org/W2145363145","https://openalex.org/W2341346307","https://openalex.org/W2154399718","https://openalex.org/W4321463377","https://openalex.org/W4312713068","https://openalex.org/W1914583973","https://openalex.org/W2768629321","https://openalex.org/W2130711276","https://openalex.org/W4308828368","https://openalex.org/W1504584981"],"abstract_inverted_index":{"Abstract":[0],"Reinforcement":[1],"learning":[2,34,148,161],"(RL)":[3],"constitutes":[4],"an":[5,71,106,140,149,162],"effective":[6],"method":[7],"of":[8,16,28,65,83,183],"controlling":[9],"dynamic":[10,49,67,151,164],"systems":[11],"without":[12],"prior":[13],"knowledge.":[14],"One":[15],"the":[17,26,63,80,100,115,127,132,136,154,173,179,184],"most":[18],"important":[19,72],"and":[20,59,181,201,225],"difficult":[21],"problems":[22,191],"in":[23,126,135,147],"RL":[24],"is":[25,37,70,145,220],"improvement":[27,129],"data":[29,81,158],"efficiency.":[30],"Probabilistic":[31],"inference":[32],"for":[33,74,187],"control":[35],"(PILCO)":[36],"a":[38,44,66,193,196,198,202,211],"state-of-the-art":[39],"data-efficient":[40],"framework":[41],"that":[42,92],"uses":[43],"Gaussian":[45],"process":[46],"to":[47,96,217],"model":[48,165],"systems.":[50],"However,":[51],"it":[52],"only":[53],"focuses":[54],"on":[55,172],"optimizing":[56],"cumulative":[57],"rewards":[58],"does":[60],"not":[61],"consider":[62],"accuracy":[64],"model,":[68],"which":[69],"factor":[73],"controller":[75,190,212],"learning.":[76],"To":[77],"further":[78],"improve":[79],"efficiency":[82,159,182],"PILCO,":[84],"we":[85,104],"propose":[86],"its":[87],"active":[88],"exploration":[89],"version":[90],"(AEPILCO)":[91],"utilizes":[93],"information":[94,107,174],"entropy":[95,108,175],"describe":[97],"samples.":[98],"In":[99],"policy":[101,117,124,128,133],"evaluation":[102,118],"stage,":[103],"incorporate":[105],"criterion":[109],"into":[110],"long-term":[111],"sample":[112,142],"prediction.":[113],"Through":[114],"informative":[116,123,141,169],"function,":[119],"our":[120],"algorithm":[121,156,186,208],"obtains":[122],"parameters":[125,134],"stage.":[130],"Using":[131],"actual":[137],"execution":[138],"produces":[139],"set;":[143],"this":[144],"helpful":[146],"accurate":[150,163],"model.":[152],"Thus,":[153],"AEPILCO":[155,207],"improves":[157],"by":[160,166],"actively":[167],"selecting":[168],"samples":[170],"based":[171],"criterion.":[176],"We":[177],"demonstrate":[178],"validity":[180],"proposed":[185],"several":[188],"challenging":[189],"involving":[192],"cart":[194,203],"pole,":[195],"pendubot,":[197],"double":[199,204],"pendulum,":[200],"pendulum.":[205],"The":[206],"can":[209],"learn":[210],"using":[213],"fewer":[214],"trials":[215],"compared":[216],"PILCO.":[218],"This":[219],"verified":[221],"through":[222],"theoretical":[223],"analysis":[224],"experimental":[226],"results.":[227]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}