{"id":"https://openalex.org/W4389459425","doi":"https://doi.org/10.1109/tetci.2023.3335944","title":"Dynamic Memory-Based Curiosity: A Bootstrap Approach for Exploration in Reinforcement Learning","display_name":"Dynamic Memory-Based Curiosity: A Bootstrap Approach for Exploration in Reinforcement Learning","publication_year":2023,"publication_date":"2023-12-07","ids":{"openalex":"https://openalex.org/W4389459425","doi":"https://doi.org/10.1109/tetci.2023.3335944"},"language":"en","primary_location":{"id":"doi:10.1109/tetci.2023.3335944","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetci.2023.3335944","pdf_url":null,"source":{"id":"https://openalex.org/S4210210251","display_name":"IEEE Transactions on Emerging Topics in Computational Intelligence","issn_l":"2471-285X","issn":["2471-285X"],"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 Emerging Topics in Computational 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/A5016262505","display_name":"Zijian Gao","orcid":"https://orcid.org/0000-0001-5151-3381"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zijian Gao","raw_affiliation_strings":["School of Computer, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"School of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102770021","display_name":"Yiying Li","orcid":"https://orcid.org/0000-0002-2632-5175"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yiying Li","raw_affiliation_strings":["Artificial Intelligence Research Center, National Innovation Institute of Defense Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Center, National Innovation Institute of Defense Technology, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013340793","display_name":"Kele Xu","orcid":"https://orcid.org/0000-0001-5997-5169"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kele Xu","raw_affiliation_strings":["School of Computer, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"School of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073132517","display_name":"Yuanzhao Zhai","orcid":"https://orcid.org/0000-0003-1385-0074"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanzhao Zhai","raw_affiliation_strings":["School of Computer, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"School of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088885490","display_name":"Bo Ding","orcid":"https://orcid.org/0000-0002-1236-8318"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Ding","raw_affiliation_strings":["School of Computer, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"School of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039795290","display_name":"Dawei Feng","orcid":"https://orcid.org/0000-0002-7587-8905"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dawei Feng","raw_affiliation_strings":["School of Computer, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"School of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083124500","display_name":"Xinjun Mao","orcid":"https://orcid.org/0000-0001-6003-5748"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinjun Mao","raw_affiliation_strings":["School of Computer, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"School of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101522100","display_name":"Huaimin Wang","orcid":"https://orcid.org/0000-0002-3245-1901"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaimin Wang","raw_affiliation_strings":["School of Computer, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"School of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5016262505"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":1.3059,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.81616129,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":"8","issue":"2","first_page":"1181","last_page":"1193"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14308","display_name":"Psychological and Educational Research Studies","score":0.9904000163078308,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T14308","display_name":"Psychological and Educational Research Studies","score":0.9904000163078308,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11135","display_name":"Virology and Viral Diseases","score":0.9423999786376953,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/curiosity","display_name":"Curiosity","score":0.9913175106048584},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.8256844282150269},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6869587302207947},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6347560286521912},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4608156085014343},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32158005237579346},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.25497937202453613},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.09646394848823547}],"concepts":[{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.9913175106048584},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.8256844282150269},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6869587302207947},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6347560286521912},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4608156085014343},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32158005237579346},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.25497937202453613},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.09646394848823547},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tetci.2023.3335944","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetci.2023.3335944","pdf_url":null,"source":{"id":"https://openalex.org/S4210210251","display_name":"IEEE Transactions on Emerging Topics in Computational Intelligence","issn_l":"2471-285X","issn":["2471-285X"],"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 Emerging Topics in Computational Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2237562141","display_name":null,"funder_award_id":"62206307","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":63,"referenced_works":["https://openalex.org/W1496462336","https://openalex.org/W1534477342","https://openalex.org/W1984685202","https://openalex.org/W2012833704","https://openalex.org/W2036107051","https://openalex.org/W2086417613","https://openalex.org/W2101524054","https://openalex.org/W2103104224","https://openalex.org/W2119333483","https://openalex.org/W2131600418","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2170899200","https://openalex.org/W2233334990","https://openalex.org/W2489939061","https://openalex.org/W2736601468","https://openalex.org/W2739512435","https://openalex.org/W2761873684","https://openalex.org/W2953326529","https://openalex.org/W2963007936","https://openalex.org/W2963359646","https://openalex.org/W2963523627","https://openalex.org/W2963979925","https://openalex.org/W2973229164","https://openalex.org/W3014596384","https://openalex.org/W3036619998","https://openalex.org/W3104276205","https://openalex.org/W3134774296","https://openalex.org/W3198317271","https://openalex.org/W4247000908","https://openalex.org/W4297098337","https://openalex.org/W4306679387","https://openalex.org/W4387546333","https://openalex.org/W6695011786","https://openalex.org/W6716474083","https://openalex.org/W6717230150","https://openalex.org/W6730641667","https://openalex.org/W6733814495","https://openalex.org/W6734097942","https://openalex.org/W6735033012","https://openalex.org/W6735443497","https://openalex.org/W6736021936","https://openalex.org/W6740092555","https://openalex.org/W6741002519","https://openalex.org/W6748603076","https://openalex.org/W6752244597","https://openalex.org/W6756303580","https://openalex.org/W6762863188","https://openalex.org/W6765240361","https://openalex.org/W6773246137","https://openalex.org/W6776556448","https://openalex.org/W6779600923","https://openalex.org/W6780470247","https://openalex.org/W6787713516","https://openalex.org/W6791000347","https://openalex.org/W6791194670","https://openalex.org/W6796667233","https://openalex.org/W6803067813","https://openalex.org/W6809799041","https://openalex.org/W6809871153","https://openalex.org/W6838568069","https://openalex.org/W6843809954","https://openalex.org/W7075998887"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347","https://openalex.org/W4210805261"],"abstract_inverted_index":{"The":[0,106],"sparsity":[1],"of":[2,28,39,195,200,227],"extrinsic":[3,183],"rewards":[4,22,43],"presents":[5,220],"a":[6,58,81,95,144,154,191,198,205],"significant":[7],"challenge":[8,38],"for":[9,62,68,118],"deep":[10],"reinforcement":[11],"learning":[12],"(DRL).":[13],"As":[14],"an":[15],"alternative,":[16],"researchers":[17],"have":[18],"focused":[19],"on":[20,153,163,197],"intrinsic":[21,42,116],"to":[23,102,232],"improve":[24],"exploration":[25],"efficiency.":[26],"One":[27],"the":[29,37,85,89,110,115,121,128,186,210,215],"most":[30],"representative":[31],"approaches":[32],"is":[33,124],"utilizing":[34],"curiosity.":[35,52],"However,":[36],"designing":[40],"effective":[41],"remains,":[44],"as":[45,114],"artificial":[46],"curiosity":[47,60,75,104,134,141],"differs":[48],"significantly":[49],"from":[50],"human":[51,74,140],"In":[53,185,214],"this":[54],"article,":[55],"we":[56,93],"introduce":[57],"novel":[59],"approach":[61],"DRL,":[63],"named":[64],"DyMeCu,":[65],"which":[66],"stands":[67],"Dynamic":[69],"Memory-based":[70],"Curiosity.":[71],"Inspired":[72],"by":[73,99,142],"and":[76,120,170,235],"information":[77,107,123],"theory,":[78],"DyMeCu":[79,136,175,189,219],"constructs":[80],"dynamic":[82,129,145],"memory":[83,146],"using":[84,143],"online":[86],"learner":[87],"following":[88],"bootstrap":[90,155],"paradigm.":[91],"Additionally,":[92],"design":[94],"two-learner":[96],"architecture":[97],"inspired":[98],"ensemble":[100],"techniques":[101],"access":[103],"better.":[105],"gap":[108],"between":[109],"two":[111,158],"learners":[112],"serves":[113],"reward":[117],"agents,":[119],"state":[122],"consistently":[125],"consolidated":[126],"into":[127],"memory.":[130],"Compared":[131],"with":[132,157,180],"previous":[133],"methods,":[135],"can":[137,148],"better":[138],"mimic":[139],"that":[147,174],"be":[149],"dynamically":[150],"grown":[151],"based":[152],"paradigm":[156],"learners.":[159],"Large-scale":[160],"empirical":[161],"experiments":[162],"multiple":[164],"benchmarks,":[165],"including":[166],"DeepMind":[167,216],"Control":[168,217],"Suite":[169],"Atari":[171,187,202],"Suite,":[172,188,218],"demonstrate":[173],"outperforms":[176],"competitive":[177],"curiosity-based":[178,233],"methods":[179,234],"or":[181],"without":[182],"rewards.":[184],"achieves":[190],"mean":[192],"human-normalized":[193],"score":[194],"5.076":[196],"subset":[199],"26":[201],"games,":[203],"achieving":[204],"77.4%":[206],"relative":[207],"improvement":[208],"over":[209],"best":[211],"other":[212,236],"baselines.":[213],"new":[221],"state-of-the-art":[222],"results":[223],"across":[224],"11":[225],"tasks":[226],"all":[228],"12":[229],"when":[230],"compared":[231],"pre-training":[237],"strategies.":[238]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}