{"id":"https://openalex.org/W2941260551","doi":"https://doi.org/10.1109/access.2019.2913001","title":"Optimistic Sampling Strategy for Data-Efficient Reinforcement Learning","display_name":"Optimistic Sampling Strategy for Data-Efficient Reinforcement Learning","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2941260551","doi":"https://doi.org/10.1109/access.2019.2913001","mag":"2941260551"},"language":"en","primary_location":{"id":"doi:10.1109/access.2019.2913001","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2913001","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08698221.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08698221.pdf","any_repository_has_fulltext":true},"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":true,"raw_author_name":"Dongfang Zhao","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, 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":["Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, 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":["Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, 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":false,"raw_author_name":"Dansong Cheng","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, 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":["Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102793120"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.1446,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.55658679,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"7","issue":null,"first_page":"55763","last_page":"55769"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9901000261306763,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9803000092506409,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8256622552871704},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7623577117919922},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6353660821914673},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.609052836894989},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5770459771156311},{"id":"https://openalex.org/keywords/cross-entropy-method","display_name":"Cross-entropy method","score":0.47022175788879395},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.448660284280777},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.43273138999938965},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4251530170440674},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.42136555910110474},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4147481322288513},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40753626823425293},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.36699196696281433},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34155356884002686},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.26065972447395325},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15332087874412537}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8256622552871704},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7623577117919922},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6353660821914673},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.609052836894989},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5770459771156311},{"id":"https://openalex.org/C75782508","wikidata":"https://www.wikidata.org/wiki/Q3333633","display_name":"Cross-entropy method","level":4,"score":0.47022175788879395},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.448660284280777},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.43273138999938965},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4251530170440674},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.42136555910110474},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4147481322288513},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40753626823425293},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.36699196696281433},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34155356884002686},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26065972447395325},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15332087874412537},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C98036226","wikidata":"https://www.wikidata.org/wiki/Q7268356","display_name":"Quadratic assignment problem","level":3,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2019.2913001","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2913001","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08698221.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:48d31e9b72f04b8d9172e2a4e4bab208","is_oa":true,"landing_page_url":"https://doaj.org/article/48d31e9b72f04b8d9172e2a4e4bab208","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 7, Pp 55763-55769 (2019)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2019.2913001","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2913001","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08698221.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6239764539","display_name":null,"funder_award_id":"61672190","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7287944521","display_name":null,"funder_award_id":"61370162","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2941260551.pdf","grobid_xml":"https://content.openalex.org/works/W2941260551.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1520597402","https://openalex.org/W2000191307","https://openalex.org/W2140135625","https://openalex.org/W2155007355","https://openalex.org/W2604726708","https://openalex.org/W2768794893","https://openalex.org/W2769877777","https://openalex.org/W2802636049","https://openalex.org/W2803767077","https://openalex.org/W2804380964","https://openalex.org/W2950614095","https://openalex.org/W2962872206","https://openalex.org/W2963634205","https://openalex.org/W2963781688","https://openalex.org/W2964043796","https://openalex.org/W3105535284","https://openalex.org/W4205513846","https://openalex.org/W4211049957","https://openalex.org/W4298159930","https://openalex.org/W4302570325","https://openalex.org/W6680657880","https://openalex.org/W6682849425","https://openalex.org/W6684205842","https://openalex.org/W6692846177","https://openalex.org/W6736742618","https://openalex.org/W6745193426","https://openalex.org/W6745600969","https://openalex.org/W6751869817","https://openalex.org/W6752089545"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W2474680198","https://openalex.org/W2970690932","https://openalex.org/W2110715801","https://openalex.org/W2054925885","https://openalex.org/W2049828308","https://openalex.org/W4255006213","https://openalex.org/W1998683226","https://openalex.org/W2597689725"],"abstract_inverted_index":{"A":[0],"high":[1],"required":[2],"number":[3],"of":[4,11,164],"interactions":[5],"with":[6,22],"the":[7,12,63,70,80,86,96,121,127],"environment":[8],"is":[9,76,99],"one":[10],"most":[13,87],"important":[14],"problems":[15,142],"in":[16,35,103,131,162],"reinforcement":[17],"learning":[18],"(RL).":[19],"To":[20],"deal":[21],"this":[23],"problem,":[24],"several":[25],"data-efficient":[26],"RL":[27],"algorithms":[28],"have":[29],"been":[30],"proposed":[31,122],"and":[32,46,105,115,148],"successfully":[33],"applied":[34],"practice.":[36],"Unlike":[37],"previous":[38],"research,":[39],"that":[40,153],"focuses":[41],"on":[42,139],"optimal":[43,58,123,155],"policy":[44,47,116],"evaluation":[45],"improvement":[48],"stages,":[49],"we":[50],"actively":[51],"select":[52],"informative":[53,88,101,134],"samples":[54,65,89],"by":[55],"leveraging":[56],"entropy-based":[57],"sampling":[59,72,124,156],"strategy,":[60],"which":[61],"takes":[62],"initial":[64,71,97,112],"set":[66],"into":[67],"consideration.":[68],"During":[69],"process,":[73],"information":[74],"entropy":[75],"used":[77],"to":[78,129],"describe":[79],"potential":[81],"samples.":[82],"The":[83,136],"agent":[84,128],"selects":[85],"using":[90],"an":[91],"optimization":[92],"method.":[93],"This":[94],"way,":[95],"sample":[98],"more":[100,110,133],"than":[102],"random":[104],"fixed":[106],"strategy.":[107],"Therefore,":[108],"a":[109,132,144,159],"accurate":[111],"dynamic":[113],"model":[114],"can":[117],"be":[118],"learned.":[119],"Thus,":[120],"method":[125],"guides":[126],"search":[130],"region.":[135],"experimental":[137],"results":[138],"standard":[140],"benchmark":[141],"involving":[143],"pendulum,":[145],"cart":[146,149],"pole,":[147],"double":[150],"pendulum":[151],"show":[152],"our":[154],"strategy":[157],"has":[158],"better":[160],"performance":[161],"terms":[163],"data":[165],"efficiency.":[166]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-15T09:29:46.208133","created_date":"2025-10-10T00:00:00"}