{"id":"https://openalex.org/W4400357656","doi":"https://doi.org/10.1631/fitee.2300548","title":"Transformer in reinforcement learning for decision-making: a survey","display_name":"Transformer in reinforcement learning for decision-making: a survey","publication_year":2024,"publication_date":"2024-06-01","ids":{"openalex":"https://openalex.org/W4400357656","doi":"https://doi.org/10.1631/fitee.2300548"},"language":"en","primary_location":{"id":"doi:10.1631/fitee.2300548","is_oa":false,"landing_page_url":"https://doi.org/10.1631/fitee.2300548","pdf_url":null,"source":{"id":"https://openalex.org/S4210189857","display_name":"Frontiers of Information Technology & Electronic Engineering","issn_l":"2095-9184","issn":["2095-9184","2095-9230"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers of Information Technology & Electronic Engineering","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/A5090802334","display_name":"Weilin Yuan","orcid":"https://orcid.org/0000-0001-9894-5253"},"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":"Weilin Yuan","raw_affiliation_strings":["College of Information and Communication, National University of Defense Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"College of Information and Communication, National University of Defense Technology, Wuhan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083082323","display_name":"Jiaxing Chen","orcid":"https://orcid.org/0000-0002-1773-5789"},"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":"Jiaxing Chen","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081802331","display_name":"Shaofei Chen","orcid":null},"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":"Shaofei Chen","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, 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":["Laboratory for Parallel and Distributed Processing, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Laboratory for Parallel and Distributed Processing, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040235604","display_name":"Zhenzhen Hu","orcid":"https://orcid.org/0000-0003-1042-8361"},"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":"Zhenzhen Hu","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108144474","display_name":"Peng Li","orcid":"https://orcid.org/0009-0003-5625-0420"},"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":"Peng Li","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100024299","display_name":"Weiwei Zhao","orcid":null},"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":"Weiwei Zhao","raw_affiliation_strings":["College of Information and Communication, National University of Defense Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"College of Information and Communication, National University of Defense Technology, Wuhan, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5090802334"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":8.0026,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.98304691,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"25","issue":"6","first_page":"763","last_page":"790"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9983999729156494,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9983999729156494,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.996999979019165,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9886999726295471,"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/materials-science","display_name":"Materials science","score":0.3205859065055847}],"concepts":[{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.3205859065055847}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1631/fitee.2300548","is_oa":false,"landing_page_url":"https://doi.org/10.1631/fitee.2300548","pdf_url":null,"source":{"id":"https://openalex.org/S4210189857","display_name":"Frontiers of Information Technology & Electronic Engineering","issn_l":"2095-9184","issn":["2095-9184","2095-9230"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers of Information Technology & Electronic Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":169,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1534120332","https://openalex.org/W1714211023","https://openalex.org/W1832693441","https://openalex.org/W1956340063","https://openalex.org/W2003281104","https://openalex.org/W2016368496","https://openalex.org/W2061344791","https://openalex.org/W2064675550","https://openalex.org/W2088956500","https://openalex.org/W2101105183","https://openalex.org/W2123301721","https://openalex.org/W2124086491","https://openalex.org/W2133564696","https://openalex.org/W2150468603","https://openalex.org/W2163605009","https://openalex.org/W2166533447","https://openalex.org/W2193104803","https://openalex.org/W2194775991","https://openalex.org/W2294092760","https://openalex.org/W2506483933","https://openalex.org/W2574978968","https://openalex.org/W2617547828","https://openalex.org/W2766447205","https://openalex.org/W2805798351","https://openalex.org/W2810602713","https://openalex.org/W2894175714","https://openalex.org/W2900120976","https://openalex.org/W2905016804","https://openalex.org/W2946794439","https://openalex.org/W2953303875","https://openalex.org/W2954742730","https://openalex.org/W2963250244","https://openalex.org/W2963341956","https://openalex.org/W2963800628","https://openalex.org/W2963925437","https://openalex.org/W2964008208","https://openalex.org/W2964081807","https://openalex.org/W2964836580","https://openalex.org/W2968831808","https://openalex.org/W2982316857","https://openalex.org/W2989847975","https://openalex.org/W2997502221","https://openalex.org/W3007769740","https://openalex.org/W3027146252","https://openalex.org/W3034999214","https://openalex.org/W3035390927","https://openalex.org/W3035624836","https://openalex.org/W3036619998","https://openalex.org/W3085139254","https://openalex.org/W3088310808","https://openalex.org/W3089090082","https://openalex.org/W3093528669","https://openalex.org/W3096609285","https://openalex.org/W3097518075","https://openalex.org/W3099518626","https://openalex.org/W3099964132","https://openalex.org/W3103334733","https://openalex.org/W3118210634","https://openalex.org/W3120778962","https://openalex.org/W3123386591","https://openalex.org/W3135593154","https://openalex.org/W3146106549","https://openalex.org/W3146366485","https://openalex.org/W3152878473","https://openalex.org/W3153094109","https://openalex.org/W3156295478","https://openalex.org/W3163842339","https://openalex.org/W3166513219","https://openalex.org/W3168892396","https://openalex.org/W3170112077","https://openalex.org/W3171125843","https://openalex.org/W3175182975","https://openalex.org/W3176814369","https://openalex.org/W3180355996","https://openalex.org/W3182829817","https://openalex.org/W3202775986","https://openalex.org/W3213789840","https://openalex.org/W3216039521","https://openalex.org/W3216752036","https://openalex.org/W4200083607","https://openalex.org/W4213019189","https://openalex.org/W4221167437","https://openalex.org/W4224324347","https://openalex.org/W4241768805","https://openalex.org/W4251283341","https://openalex.org/W4252284432","https://openalex.org/W4252801674","https://openalex.org/W4281636288","https://openalex.org/W4283794074","https://openalex.org/W4283815845","https://openalex.org/W4285179996","https://openalex.org/W4285218426","https://openalex.org/W4285231868","https://openalex.org/W4285393899","https://openalex.org/W4290652759","https://openalex.org/W4291414411","https://openalex.org/W4295356277","https://openalex.org/W4296513000","https://openalex.org/W4297812239","https://openalex.org/W4306680355","https://openalex.org/W4306955484","https://openalex.org/W4310282800","https://openalex.org/W4310390787","https://openalex.org/W4312578548","https://openalex.org/W4312879418","https://openalex.org/W4312909062","https://openalex.org/W4313043552","https://openalex.org/W4317892538","https://openalex.org/W4322775461","https://openalex.org/W4362519158","https://openalex.org/W4362603432","https://openalex.org/W4386815404","https://openalex.org/W4389667622","https://openalex.org/W4391944659","https://openalex.org/W4394698525","https://openalex.org/W6600007113","https://openalex.org/W6600050674","https://openalex.org/W6600135713","https://openalex.org/W6600137863","https://openalex.org/W6600212061","https://openalex.org/W6600234944","https://openalex.org/W6600302053","https://openalex.org/W6600424091","https://openalex.org/W6600438989","https://openalex.org/W6600466347","https://openalex.org/W6600511658","https://openalex.org/W6600669965","https://openalex.org/W6600721014","https://openalex.org/W6600783858","https://openalex.org/W6600828087","https://openalex.org/W6600988277","https://openalex.org/W6600994665","https://openalex.org/W6601065604","https://openalex.org/W6601128452","https://openalex.org/W6601141708","https://openalex.org/W6601144205","https://openalex.org/W6601328799","https://openalex.org/W6601636429","https://openalex.org/W6602480875","https://openalex.org/W6602646459","https://openalex.org/W6603732165","https://openalex.org/W6604065363","https://openalex.org/W6604208927","https://openalex.org/W6604663618","https://openalex.org/W6605730092","https://openalex.org/W6605946209","https://openalex.org/W6606876336","https://openalex.org/W6630858386","https://openalex.org/W6631495455","https://openalex.org/W6632923821","https://openalex.org/W6634101208","https://openalex.org/W6636946117","https://openalex.org/W6653085483","https://openalex.org/W6682631176","https://openalex.org/W6683443546","https://openalex.org/W6725794755","https://openalex.org/W6730126202","https://openalex.org/W6732578804","https://openalex.org/W6762050013","https://openalex.org/W6780161852","https://openalex.org/W6787268631","https://openalex.org/W6810745647","https://openalex.org/W6814003322","https://openalex.org/W6816280849","https://openalex.org/W6818723395","https://openalex.org/W6835070974","https://openalex.org/W6838836181","https://openalex.org/W7026488684"],"related_works":["https://openalex.org/W4246450666","https://openalex.org/W4388998267","https://openalex.org/W2898370298","https://openalex.org/W2137437058","https://openalex.org/W4396520874","https://openalex.org/W4390401159","https://openalex.org/W2744391499","https://openalex.org/W4230250635","https://openalex.org/W3041790586","https://openalex.org/W2018879842"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"has":[3,10],"become":[4],"a":[5,23,63,126,145],"dominant":[6],"decision-making":[7,32,75,172],"paradigm":[8],"and":[9,45,87,106,151,179],"achieved":[11],"notable":[12],"success":[13,38],"in":[14,26,30,41,74,135,156,170],"many":[15],"real-world":[16],"applications.":[17],"Notably,":[18],"deep":[19],"neural":[20],"networks":[21],"play":[22],"crucial":[24],"role":[25],"unlocking":[27],"RL\u2019s":[28],"potential":[29],"large-scale":[31],"tasks.":[33],"Inspired":[34],"by":[35,53],"current":[36,103],"major":[37],"of":[39,67,129,148,159,165],"Transformer":[40,55,132],"natural":[42],"language":[43],"processing":[44],"computer":[46],"vision,":[47],"numerous":[48],"bottlenecks":[49],"have":[50],"been":[51],"overcome":[52],"combining":[54],"with":[56,101,113],"RL":[57,70,104,136,154],"for":[58,137],"decision-making.":[59,138],"This":[60],"paper":[61],"presents":[62],"multiangle":[64],"systematic":[65],"survey":[66,143],"various":[68],"Transformer-based":[69],"(TransRL)":[71],"models":[72,150],"applied":[73],"tasks,":[76],"including":[77],"basic":[78],"models,":[79],"advanced":[80],"algorithms,":[81],"representative":[82],"implementation":[83],"instances,":[84],"typical":[85],"applications,":[86],"known":[88],"challenges.":[89],"Our":[90],"work":[91],"aims":[92],"to":[93,124],"provide":[94],"insights":[95],"into":[96],"problems":[97],"that":[98,141],"inherently":[99],"arise":[100],"the":[102,122,130,153,166,171,176],"approaches,":[105],"examines":[107],"how":[108],"we":[109,120,174],"can":[110],"address":[111],"them":[112],"better":[114],"TransRL":[115,149,168],"models.":[116],"To":[117,162],"our":[118],"knowledge,":[119],"are":[121],"first":[123],"present":[125],"comprehensive":[127,146],"review":[128,147],"recent":[131],"research":[133],"developments":[134,169],"We":[139],"hope":[140],"this":[142],"provides":[144],"inspires":[152],"community":[155],"its":[157],"pursuit":[158],"future":[160],"directions.":[161],"keep":[163],"track":[164],"rapid":[167],"domains,":[173],"summarize":[175],"latest":[177],"papers":[178],"their":[180],"open-source":[181],"implementations":[182],"at":[183],"https://github.com/williamyuanv0/Transformer-in-Reinforcement-Learning-for-Decision-Making-A-Survey":[184],".":[185]},"counts_by_year":[{"year":2026,"cited_by_count":20},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2024-07-06T00:00:00"}