{"id":"https://openalex.org/W4220652971","doi":"https://doi.org/10.1109/tnnls.2022.3151412","title":"Learning a World Model With Multitimescale Memory Augmentation","display_name":"Learning a World Model With Multitimescale Memory Augmentation","publication_year":2022,"publication_date":"2022-03-07","ids":{"openalex":"https://openalex.org/W4220652971","doi":"https://doi.org/10.1109/tnnls.2022.3151412","pmid":"https://pubmed.ncbi.nlm.nih.gov/35254991"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2022.3151412","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2022.3151412","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5059258252","display_name":"Wenzhe Cai","orcid":"https://orcid.org/0000-0003-4610-3454"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenzhe Cai","raw_affiliation_strings":["School of Automation, Southeast University, Nanjing, China","Peng Cheng Laboratory (PCL), Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-4610-3454","affiliations":[{"raw_affiliation_string":"School of Automation, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"Peng Cheng Laboratory (PCL), Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101506354","display_name":"Teng Wang","orcid":"https://orcid.org/0000-0002-1802-0435"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Teng Wang","raw_affiliation_strings":["School of Automation, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-1802-0435","affiliations":[{"raw_affiliation_string":"School of Automation, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100388745","display_name":"Jiawei Wang","orcid":"https://orcid.org/0000-0001-5037-4658"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawei Wang","raw_affiliation_strings":["School of Control Science and Engineering, Tongji University, Shanghai, China","Peng Cheng Laboratory (PCL), Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-5037-4658","affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"Peng Cheng Laboratory (PCL), Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019248683","display_name":"Changyin Sun","orcid":"https://orcid.org/0000-0001-9269-334X"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changyin Sun","raw_affiliation_strings":["School of Automation, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-9269-334X","affiliations":[{"raw_affiliation_string":"School of Automation, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5059258252"],"corresponding_institution_ids":["https://openalex.org/I4210136793","https://openalex.org/I76569877"],"apc_list":null,"apc_paid":null,"fwci":0.6937,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.74193598,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"34","issue":"11","first_page":"8493","last_page":"8502"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9970999956130981,"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":0.9970999956130981,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.972599983215332,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/computer-science","display_name":"Computer science","score":0.7920817732810974},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6619766354560852},{"id":"https://openalex.org/keywords/memory-model","display_name":"Memory model","score":0.6098754405975342},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6074246168136597},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5440028309822083},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5375504493713379},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4695585072040558},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4590964913368225},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4405054450035095},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4357045590877533},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4294438660144806},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.4169352650642395}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7920817732810974},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6619766354560852},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.6098754405975342},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6074246168136597},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5440028309822083},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5375504493713379},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4695585072040558},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4590964913368225},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4405054450035095},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4357045590877533},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4294438660144806},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.4169352650642395},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2022.3151412","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2022.3151412","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:35254991","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35254991","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1586809628","display_name":null,"funder_award_id":"2018AAA0101400","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5033343354","display_name":null,"funder_award_id":"61921004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7121147207","display_name":null,"funder_award_id":"BK20202006","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":67,"referenced_works":["https://openalex.org/W764651262","https://openalex.org/W1903029394","https://openalex.org/W2118688707","https://openalex.org/W2145339207","https://openalex.org/W2201581102","https://openalex.org/W2257979135","https://openalex.org/W2528489519","https://openalex.org/W2560474170","https://openalex.org/W2596982695","https://openalex.org/W2606047872","https://openalex.org/W2607014226","https://openalex.org/W2724169821","https://openalex.org/W2736601468","https://openalex.org/W2761873684","https://openalex.org/W2781726626","https://openalex.org/W2787938642","https://openalex.org/W2885550588","https://openalex.org/W2895453875","https://openalex.org/W2902125520","https://openalex.org/W2920362155","https://openalex.org/W2949475445","https://openalex.org/W2963095800","https://openalex.org/W2963224068","https://openalex.org/W2963276097","https://openalex.org/W2963523627","https://openalex.org/W2963891416","https://openalex.org/W2963940252","https://openalex.org/W2964067469","https://openalex.org/W2964094092","https://openalex.org/W2964156315","https://openalex.org/W2967043539","https://openalex.org/W2982316857","https://openalex.org/W2995298643","https://openalex.org/W2995429865","https://openalex.org/W2997289589","https://openalex.org/W3004691725","https://openalex.org/W3035479686","https://openalex.org/W3101596791","https://openalex.org/W4287867830","https://openalex.org/W4289294484","https://openalex.org/W4297797010","https://openalex.org/W4298157202","https://openalex.org/W6677477928","https://openalex.org/W6687681856","https://openalex.org/W6717230150","https://openalex.org/W6729495853","https://openalex.org/W6730111887","https://openalex.org/W6730641667","https://openalex.org/W6735033012","https://openalex.org/W6736803224","https://openalex.org/W6740092555","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6748638692","https://openalex.org/W6748839928","https://openalex.org/W6750253780","https://openalex.org/W6750642828","https://openalex.org/W6753925943","https://openalex.org/W6756256016","https://openalex.org/W6756303580","https://openalex.org/W6756908582","https://openalex.org/W6760405395","https://openalex.org/W6769580333","https://openalex.org/W6770086194","https://openalex.org/W6771217966","https://openalex.org/W6771807793","https://openalex.org/W6773029903"],"related_works":["https://openalex.org/W3125011624","https://openalex.org/W1508631387","https://openalex.org/W2370917603","https://openalex.org/W2952760143","https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2017776670","https://openalex.org/W2347897961","https://openalex.org/W2138720691"],"abstract_inverted_index":{"Model-based":[0],"reinforcement":[1],"learning":[2],"(RL)":[3],"is":[4,130,152,169],"regarded":[5],"as":[6,110],"a":[7,57,81,134,191],"promising":[8],"approach":[9,168],"to":[10,67,79,86,119,125,140,159,171,209,215],"tackle":[11],"the":[12,26,29,95,106,111,122,142,156,183,198,206,217],"challenges":[13],"that":[14,53,166],"hinder":[15],"model-free":[16,218],"RL.":[17],"The":[18,149],"success":[19],"of":[20,28,98,114,200],"model-based":[21],"RL":[22,219],"hinges":[23],"critically":[24],"on":[25],"quality":[27],"predicted":[30,207],"dynamic":[31],"models.":[32],"However,":[33],"for":[34],"many":[35],"real-world":[36],"tasks":[37],"involving":[38],"high-dimensional":[39],"state":[40],"spaces,":[41],"current":[42],"dynamics":[43],"prediction":[44,138,188],"models":[45],"show":[46,165],"poor":[47],"performance":[48],"in":[49,176,187],"long-term":[50,69,96,157,174],"prediction.":[51],"To":[52],"end,":[54],"we":[55,75,104,195],"propose":[56],"novel":[58],"two-branch":[59],"neural":[60,83],"network":[61,84],"architecture":[62,85],"with":[63],"multi-timescale":[64],"memory":[65,72,97,113,158],"augmentation":[66],"handle":[68],"and":[70,116,181],"short-term":[71,112],"differently.":[73],"Specifically,":[74],"follow":[76],"previous":[77,102],"works":[78],"introduce":[80],"recurrent":[82],"encode":[87],"history":[88],"observation":[89,151],"sequences":[90],"into":[91],"latent":[92],"space,":[93],"characterizing":[94],"agents.":[99],"Different":[100],"from":[101],"works,":[103],"view":[105],"most":[107],"recent":[108],"observations":[109],"agents":[115],"employ":[117],"them":[118],"directly":[120],"reconstruct":[121],"next":[123],"frame":[124],"avoid":[126],"compounding":[127],"error.":[128],"This":[129],"achieved":[131],"by":[132,155,190,204],"introducing":[133],"self-supervised":[135],"optical":[136],"flow":[137],"structure":[139],"model":[141,203],"action-conditional":[143],"feature":[144],"transformation":[145],"at":[146],"pixel":[147],"level.":[148],"reconstructed":[150],"finally":[153],"augmented":[154],"ensure":[160],"semantic":[161],"consistency.":[162],"Experimental":[163],"results":[164],"our":[167,201],"able":[170],"generate":[172],"visually-realistic":[173],"predictions":[175],"DeepMind":[177],"maze":[178],"navigation":[179],"games,":[180],"outperforms":[182],"prevalent":[184],"state-of-the-art":[185],"methods":[186],"accuracy":[189],"large":[192],"margin.":[193],"Furthermore,":[194],"also":[196],"evaluate":[197],"usefulness":[199],"world":[202],"using":[205],"frames":[208],"drive":[210],"an":[211],"imagination-augmented":[212],"exploration":[213],"strategy":[214],"improve":[216],"controller.":[220]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}