{"id":"https://openalex.org/W4390672436","doi":"https://doi.org/10.1007/s44196-023-00389-1","title":"Active Exploration Deep Reinforcement Learning for Continuous Action Space with Forward Prediction","display_name":"Active Exploration Deep Reinforcement Learning for Continuous Action Space with Forward Prediction","publication_year":2024,"publication_date":"2024-01-08","ids":{"openalex":"https://openalex.org/W4390672436","doi":"https://doi.org/10.1007/s44196-023-00389-1"},"language":"en","primary_location":{"id":"doi:10.1007/s44196-023-00389-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44196-023-00389-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44196-023-00389-1.pdf","source":{"id":"https://openalex.org/S190680769","display_name":"International Journal of Computational Intelligence Systems","issn_l":"1875-6883","issn":["1875-6883","1875-6891"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computational Intelligence Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1007/s44196-023-00389-1.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103239424","display_name":"Dongfang Zhao","orcid":"https://orcid.org/0000-0003-4863-6414"},"institutions":[{"id":"https://openalex.org/I179026463","display_name":"Beijing Technology and Business University","ror":"https://ror.org/013e0zm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I179026463"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dongfang Zhao","raw_affiliation_strings":["School of Computer science and Engineering, Beijing Technology and Business University, Fucheng Road, Haidian District, Beijing, 100048, China"],"raw_orcid":"https://orcid.org/0000-0003-4863-6414","affiliations":[{"raw_affiliation_string":"School of Computer science and Engineering, Beijing Technology and Business University, Fucheng Road, Haidian District, Beijing, 100048, China","institution_ids":["https://openalex.org/I179026463"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093694333","display_name":"Xu Huanshi","orcid":null},"institutions":[{"id":"https://openalex.org/I179026463","display_name":"Beijing Technology and Business University","ror":"https://ror.org/013e0zm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I179026463"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Huanshi","raw_affiliation_strings":["School of Computer science and Engineering, Beijing Technology and Business University, Fucheng Road, Haidian District, Beijing, 100048, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer science and Engineering, Beijing Technology and Business University, Fucheng Road, Haidian District, Beijing, 100048, China","institution_ids":["https://openalex.org/I179026463"]}]},{"author_position":"last","author":{"id":null,"display_name":"Zhang Xun","orcid":null},"institutions":[{"id":"https://openalex.org/I179026463","display_name":"Beijing Technology and Business University","ror":"https://ror.org/013e0zm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I179026463"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang Xun","raw_affiliation_strings":["School of Computer science and Engineering, Beijing Technology and Business University, Fucheng Road, Haidian District, Beijing, 100048, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer science and Engineering, Beijing Technology and Business University, Fucheng Road, Haidian District, Beijing, 100048, China","institution_ids":["https://openalex.org/I179026463"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103239424"],"corresponding_institution_ids":["https://openalex.org/I179026463"],"apc_list":{"value":1390,"currency":"GBP","value_usd":1704},"apc_paid":{"value":1390,"currency":"GBP","value_usd":1704},"fwci":1.2588,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.81455259,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"17","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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":0.9991999864578247,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9807000160217285,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9731000065803528,"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":0.8476666212081909},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7447527647018433},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7371164560317993},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.6959746479988098},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6067699193954468},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5485532879829407},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5457550287246704},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5310514569282532},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5235702395439148},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.47407427430152893},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.467099130153656},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44847744703292847},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.4311670958995819},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.42879951000213623},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.2596723437309265},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13291332125663757},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10491463541984558}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8476666212081909},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7447527647018433},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7371164560317993},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.6959746479988098},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6067699193954468},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5485532879829407},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5457550287246704},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5310514569282532},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5235702395439148},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.47407427430152893},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.467099130153656},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44847744703292847},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4311670958995819},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.42879951000213623},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.2596723437309265},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13291332125663757},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10491463541984558},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s44196-023-00389-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44196-023-00389-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44196-023-00389-1.pdf","source":{"id":"https://openalex.org/S190680769","display_name":"International Journal of Computational Intelligence Systems","issn_l":"1875-6883","issn":["1875-6883","1875-6891"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computational Intelligence Systems","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:b489d98dc81c4b269c6963c233b413de","is_oa":true,"landing_page_url":"https://doaj.org/article/b489d98dc81c4b269c6963c233b413de","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Journal of Computational Intelligence Systems, Vol 17, Iss 1, Pp 1-8 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s44196-023-00389-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44196-023-00389-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44196-023-00389-1.pdf","source":{"id":"https://openalex.org/S190680769","display_name":"International Journal of Computational Intelligence Systems","issn_l":"1875-6883","issn":["1875-6883","1875-6891"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computational Intelligence Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3173189656","display_name":null,"funder_award_id":"42101470","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5379183933","display_name":null,"funder_award_id":"72242106","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390672436.pdf"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W2000191307","https://openalex.org/W2127572219","https://openalex.org/W2134491302","https://openalex.org/W2169209873","https://openalex.org/W2746553466","https://openalex.org/W2963523627","https://openalex.org/W3164005523","https://openalex.org/W3195968524","https://openalex.org/W6600710202","https://openalex.org/W6629994015","https://openalex.org/W6814003322"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W2015051472","https://openalex.org/W2168501056","https://openalex.org/W1965695708","https://openalex.org/W2120009678","https://openalex.org/W2912947802","https://openalex.org/W2037601570","https://openalex.org/W2123856982","https://openalex.org/W1530089576"],"abstract_inverted_index":{"Abstract":[0],"The":[1,168,188],"application":[2],"of":[3,10,67,106,116,135],"reinforcement":[4,89],"learning":[5,90],"(RL)":[6],"to":[7,34,42,60,98,162],"the":[8,20,26,80,95,103,114,117,121,133,136],"field":[9],"autonomous":[11],"robotics":[12],"has":[13],"high":[14],"requirements":[15],"about":[16],"sample":[17,31,201],"efficiency,":[18],"since":[19],"agent":[21],"expends":[22],"for":[23,30,79,127,157],"interaction":[24],"with":[25],"environment.":[27],"One":[28],"method":[29,93,153],"efficiency":[32],"is":[33,111,124,141,154,172],"extract":[35],"knowledge":[36,51],"from":[37],"existing":[38],"samples":[39,129],"and":[40,65,183,197,200],"used":[41],"exploration.":[43],"Typical":[44],"RL":[45,77],"algorithms":[46],"achieve":[47],"exploration":[48,54,75,87,140,152],"using":[49,194],"task-specific":[50],"or":[52],"adding":[53],"noise.":[55],"These":[56],"methods":[57],"are":[58],"limited":[59],"current":[61],"policy":[62],"improvement":[63],"level":[64],"lack":[66],"long-term":[68,144,149],"planning.":[69],"We":[70],"propose":[71],"a":[72,192],"novel":[73],"active":[74,86],"deep":[76,88],"algorithm":[78,171],"continuous":[81],"action":[82,146,151,166],"space":[83],"problem":[84,182],"named":[85],"(AEDRL).":[91],"Our":[92],"uses":[94],"Gaussian":[96],"process":[97],"model":[99],"dynamic":[100,137],"model,":[101],"enabling":[102],"probability":[104],"description":[105],"prediction":[107],"sample.":[108],"Action":[109],"selection":[110],"formulated":[112],"as":[113],"solution":[115],"optimization":[118,122],"problem.":[119],"Thus,":[120],"objective":[123],"specifically":[125],"designed":[126],"selecting":[128],"that":[130],"can":[131,190],"minimize":[132],"uncertainty":[134],"model.":[138],"Active":[139],"achieved":[142],"through":[143],"optimized":[145],"selection.":[147],"This":[148],"considered":[150],"more":[155,164],"guidance":[156],"learning.":[158],"Enable":[159],"intelligent":[160],"agents":[161],"explore":[163],"interesting":[165],"spaces.":[167],"proposed":[169],"AEDRL":[170,189],"evaluated":[173],"on":[174],"several":[175],"robotic":[176],"control":[177],"task":[178],"including":[179],"classic":[180],"pendulum":[181],"five":[184],"complex":[185],"articulated":[186],"robots.":[187],"learn":[191],"controller":[193],"fewer":[195],"episodes":[196],"demonstrates":[198],"performance":[199],"efficiency.":[202]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}