{"id":"https://openalex.org/W4366493064","doi":"https://doi.org/10.1109/tai.2023.3268612","title":"Sample Efficient Reinforcement Learning Using Graph-Based Memory Reconstruction","display_name":"Sample Efficient Reinforcement Learning Using Graph-Based Memory Reconstruction","publication_year":2023,"publication_date":"2023-04-20","ids":{"openalex":"https://openalex.org/W4366493064","doi":"https://doi.org/10.1109/tai.2023.3268612"},"language":"en","primary_location":{"id":"doi:10.1109/tai.2023.3268612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2023.3268612","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080641582","display_name":"Yongxin Kang","orcid":"https://orcid.org/0000-0002-0468-9234"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yongxin Kang","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055979604","display_name":"Enmin Zhao","orcid":"https://orcid.org/0000-0001-6117-5080"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Enmin Zhao","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049451354","display_name":"Yifan Zang","orcid":"https://orcid.org/0000-0003-4537-384X"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Zang","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100419693","display_name":"Lijuan Li","orcid":"https://orcid.org/0000-0002-2758-7433"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lijuan Li","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100400000","display_name":"Kai Li","orcid":"https://orcid.org/0000-0003-3840-3270"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Li","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090751520","display_name":"Pin Tao","orcid":"https://orcid.org/0000-0003-2687-7997"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pin Tao","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076090670","display_name":"Junliang Xing","orcid":"https://orcid.org/0000-0001-6801-0510"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junliang Xing","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5080641582"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879","https://openalex.org/I4210100255","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.8741,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.77775187,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"5","issue":"2","first_page":"751","last_page":"762"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9412000179290771,"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":0.9412000179290771,"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/T10581","display_name":"Neural dynamics and brain function","score":0.9402999877929688,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10241","display_name":"Functional Brain Connectivity Studies","score":0.9114999771118164,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.841325581073761},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8032705783843994},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5834550857543945},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5680341720581055},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.553024411201477},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.48892727494239807},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.45643484592437744},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43532052636146545},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4213513731956482},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.38639575242996216},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.10251417756080627},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07907861471176147}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.841325581073761},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8032705783843994},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5834550857543945},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5680341720581055},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.553024411201477},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.48892727494239807},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.45643484592437744},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43532052636146545},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4213513731956482},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.38639575242996216},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.10251417756080627},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07907861471176147},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tai.2023.3268612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2023.3268612","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4257201797","display_name":null,"funder_award_id":"62222606","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5475552240","display_name":null,"funder_award_id":"61902402","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G998127002","display_name":null,"funder_award_id":"62076238","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":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1737672083","https://openalex.org/W1984904891","https://openalex.org/W1996797695","https://openalex.org/W2003331117","https://openalex.org/W2036216970","https://openalex.org/W2047057213","https://openalex.org/W2047699328","https://openalex.org/W2086600750","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2165558283","https://openalex.org/W2169528473","https://openalex.org/W2436711315","https://openalex.org/W2605615531","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2766447205","https://openalex.org/W2809097245","https://openalex.org/W2810563302","https://openalex.org/W2902907165","https://openalex.org/W2953204260","https://openalex.org/W2953311973","https://openalex.org/W2962810718","https://openalex.org/W2964082094","https://openalex.org/W2982316857","https://openalex.org/W2998470023","https://openalex.org/W2999741028","https://openalex.org/W3006432778","https://openalex.org/W3011120880","https://openalex.org/W3150917758","https://openalex.org/W3174888375","https://openalex.org/W3175870124","https://openalex.org/W3189480080","https://openalex.org/W4211128281","https://openalex.org/W4214717370","https://openalex.org/W4251731575","https://openalex.org/W6685444567","https://openalex.org/W6687681856","https://openalex.org/W6692846177","https://openalex.org/W6718359804","https://openalex.org/W6734330393","https://openalex.org/W6740801417","https://openalex.org/W6741002519","https://openalex.org/W6754184789","https://openalex.org/W6755289019","https://openalex.org/W6760405395","https://openalex.org/W6761665040","https://openalex.org/W6763356705","https://openalex.org/W6772744401","https://openalex.org/W6775686901","https://openalex.org/W6791277150","https://openalex.org/W6802704075","https://openalex.org/W6922480057"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W20361778","https://openalex.org/W2024136090","https://openalex.org/W2964765435"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,25,53],"(RL)":[2],"algorithms":[3],"typically":[4],"require":[5],"orders":[6],"of":[7],"magnitude":[8],"more":[9],"interactions":[10,133],"than":[11],"humans":[12],"to":[13,59,70,107,123,172],"learn":[14,124],"effective":[15],"policies.":[16],"Research":[17],"on":[18,56,97],"memory":[19,45,72,86,100],"in":[20,75,147,176],"neuroscience":[21],"suggests":[22],"that":[23],"humans'":[24],"efficiency":[26],"benefits":[27],"from":[28],"associating":[29],"their":[30],"experiences":[31],"and":[32,49,101,109,131,145,151,169],"reconstructing":[33,138],"potential":[34,111],"events.":[35],"Inspired":[36],"by":[37,137],"this":[38,57,66,177],"finding,":[39],"we":[40,77],"introduce":[41],"a":[42,51],"human":[43],"brainlike":[44],"structure":[46,58],"for":[47],"agents":[48],"build":[50,108],"general":[52],"framework":[54,67,83],"based":[55],"improve":[60],"the":[61,71,79,98,120,135,148,166],"RL":[62,82,121,161],"sampling":[63],"efficiency.":[64],"Since":[65],"is":[68],"similar":[69],"reconstruction":[73,87],"process":[74],"psychology,":[76],"name":[78],"newly":[80],"proposed":[81],"as":[84],"graph-based":[85],"(GBMR).":[88],"In":[89],"particular,":[90],"GBMR":[91],"first":[92],"maintains":[93],"an":[94],"attribute":[95],"graph":[96],"agent's":[99],"then":[102],"retrieves":[103],"its":[104,127,139],"critical":[105],"nodes":[106],"update":[110],"paths":[112],"among":[113],"these":[114],"nodes.":[115],"This":[116],"novel":[117],"pipeline":[118],"drives":[119],"agent":[122],"faster":[125],"with":[126,134],"memory-enhanced":[128],"value":[129],"functions":[130],"reduces":[132],"environment":[136],"valuable":[140],"paths.":[141],"Extensive":[142],"experimental":[143],"analyses":[144],"evaluations":[146],"grid":[149],"maze":[150],"some":[152],"challenging":[153],"Atari":[154],"environments":[155],"demonstrate":[156],"GBMRs":[157],"superiority":[158],"over":[159],"traditional":[160],"methods.":[162],"We":[163],"will":[164],"release":[165],"source":[167],"code":[168],"trained":[170],"models":[171],"facilitate":[173],"further":[174],"studies":[175],"research":[178],"direction.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}