{"id":"https://openalex.org/W4385488636","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191774","title":"Elastic step DDPG: Multi-step reinforcement learning for improved sample efficiency","display_name":"Elastic step DDPG: Multi-step reinforcement learning for improved sample efficiency","publication_year":2023,"publication_date":"2023-06-18","ids":{"openalex":"https://openalex.org/W4385488636","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191774"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn54540.2023.10191774","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn54540.2023.10191774","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/conference_contribution/Elastic_step_DDPG_Multi-step_reinforcement_learning_for_improved_sample_efficiency/23972622","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080764819","display_name":"Adrian Ly","orcid":null},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Adrian Ly","raw_affiliation_strings":["School of Information Technology, Deakin University,Geelong,Australia","School of Information Technology, Deakin University, Geelong, Australia"],"affiliations":[{"raw_affiliation_string":"School of Information Technology, Deakin University,Geelong,Australia","institution_ids":["https://openalex.org/I149704539"]},{"raw_affiliation_string":"School of Information Technology, Deakin University, Geelong, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032749222","display_name":"Richard Dazeley","orcid":"https://orcid.org/0000-0002-6199-9685"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Richard Dazeley","raw_affiliation_strings":["School of Information Technology, Deakin University,Geelong,Australia","School of Information Technology, Deakin University, Geelong, Australia"],"affiliations":[{"raw_affiliation_string":"School of Information Technology, Deakin University,Geelong,Australia","institution_ids":["https://openalex.org/I149704539"]},{"raw_affiliation_string":"School of Information Technology, Deakin University, Geelong, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080095540","display_name":"Peter Vamplew","orcid":"https://orcid.org/0000-0002-8687-4424"},"institutions":[{"id":"https://openalex.org/I149672521","display_name":"Federation University","ror":"https://ror.org/05qbzwv83","country_code":"AU","type":"education","lineage":["https://openalex.org/I149672521"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Peter Vamplew","raw_affiliation_strings":["Federation University,Centre for Smart Analytics,Ballarat,Australia","Centre for Smart Analytics, Federation University, Ballarat, Australia"],"affiliations":[{"raw_affiliation_string":"Federation University,Centre for Smart Analytics,Ballarat,Australia","institution_ids":["https://openalex.org/I149672521"]},{"raw_affiliation_string":"Centre for Smart Analytics, Federation University, Ballarat, Australia","institution_ids":["https://openalex.org/I149672521"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101915335","display_name":"Francisco Cruz","orcid":"https://orcid.org/0000-0002-0206-832X"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Francisco Cruz","raw_affiliation_strings":["University of New South Wales,Computer Science and Engineering,Sydney,Australia","Computer Science and Engineering, University of New South Wales, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"University of New South Wales,Computer Science and Engineering,Sydney,Australia","institution_ids":["https://openalex.org/I31746571"]},{"raw_affiliation_string":"Computer Science and Engineering, University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038741954","display_name":"Sunil Aryal","orcid":"https://orcid.org/0000-0002-6639-6824"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sunil Aryal","raw_affiliation_strings":["School of Information Technology, Deakin University,Geelong,Australia","School of Information Technology, Deakin University, Geelong, Australia"],"affiliations":[{"raw_affiliation_string":"School of Information Technology, Deakin University,Geelong,Australia","institution_ids":["https://openalex.org/I149704539"]},{"raw_affiliation_string":"School of Information Technology, Deakin University, Geelong, Australia","institution_ids":["https://openalex.org/I149704539"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5080764819"],"corresponding_institution_ids":["https://openalex.org/I149704539"],"apc_list":null,"apc_paid":null,"fwci":0.5211,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.71252023,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"01","last_page":"06"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9950000047683716,"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":0.979200005531311,"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":0.7470051050186157},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6560807228088379},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6248022317886353},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6146027445793152},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.45787757635116577},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4012315571308136},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3391878008842468},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2791467308998108},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0650133490562439}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7470051050186157},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6560807228088379},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6248022317886353},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6146027445793152},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.45787757635116577},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4012315571308136},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3391878008842468},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2791467308998108},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0650133490562439},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ijcnn54540.2023.10191774","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn54540.2023.10191774","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:vital:18667","is_oa":false,"landing_page_url":"http://researchonline.federation.edu.au/vital/access/HandleResolver/1959.17/196193","pdf_url":null,"source":{"id":"https://openalex.org/S4306400234","display_name":"FedUni ResearchOnline (Federation University Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210158496","host_organization_name":"Australian Federation of University Women \u2013 South Australia","host_organization_lineage":["https://openalex.org/I4210158496"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:figshare.com:article/23972622","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Elastic_step_DDPG_Multi-step_reinforcement_learning_for_improved_sample_efficiency/23972622","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/23972622","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Elastic_step_DDPG_Multi-step_reinforcement_learning_for_improved_sample_efficiency/23972622","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1507563178","https://openalex.org/W2145339207","https://openalex.org/W2201581102","https://openalex.org/W2761873684","https://openalex.org/W2766447205","https://openalex.org/W2775482448","https://openalex.org/W2877093712","https://openalex.org/W2963864421","https://openalex.org/W2998544442","https://openalex.org/W3006670279","https://openalex.org/W3042365678","https://openalex.org/W3128125614","https://openalex.org/W3133441015","https://openalex.org/W3160355689","https://openalex.org/W3162026808","https://openalex.org/W4283639886","https://openalex.org/W4390413862","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6687681856","https://openalex.org/W6735506055","https://openalex.org/W6748839928","https://openalex.org/W6771936881","https://openalex.org/W6780404908","https://openalex.org/W6780559895","https://openalex.org/W6780871695","https://openalex.org/W6796426860"],"related_works":["https://openalex.org/W2051487156","https://openalex.org/W2073681303","https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474"],"abstract_inverted_index":{"A":[0],"major":[1],"challenge":[2],"in":[3,74],"deep":[4],"reinforcement":[5],"learning":[6],"is":[7,27,64,102,130,141],"that":[8,62,126],"it":[9,63],"requires":[10],"more":[11,92,142],"data":[12],"to":[13,15,23,28,32,39,41,50,55,66,76,104,132],"converge":[14,40],"an":[16],"policy":[17,139],"for":[18],"complex":[19,93],"problems.":[20],"One":[21],"way":[22],"improve":[24],"sample":[25,143],"efficiency":[26],"use":[29],"n-step":[30,46],"updates":[31,47],"reduce":[33],"the":[34,68,84,87,112,120],"number":[35],"of":[36,70,86],"samples":[37],"required":[38],"a":[42,134],"good":[43],"policy.":[44],"However":[45],"are":[48],"known":[49],"be":[51,105],"brittle":[52],"and":[53,95,123,140],"difficult":[54],"tune.":[56],"Elastic":[57,116,127],"Step":[58,117,128],"DQN":[59,75,118],"has":[60],"shown":[61],"possible":[65],"automate":[67],"value":[69],"<tex":[71],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[72],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$n$</tex>":[73],"solve":[77],"problems":[78,94,97],"involving":[79],"discrete":[80],"action":[81,100],"spaces,":[82],"however":[83],"efficacy":[85],"technique":[88],"when":[89],"applied":[90],"on":[91],"against":[96],"with":[98],"continuous":[99],"spaces":[101],"yet":[103],"shown.":[106],"In":[107],"this":[108],"paper":[109],"we":[110],"adapt":[111],"innovations":[113],"proposed":[114],"by":[115],"onto":[119],"DDPG":[121,129],"algorithm":[122],"show":[124],"empirically":[125],"able":[131],"achieve":[133],"much":[135],"stronger":[136],"final":[137],"training":[138],"efficient":[144],"than":[145],"DDPG.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}