{"id":"https://openalex.org/W4399310716","doi":"https://doi.org/10.1109/tpami.2024.3408271","title":"On Transforming Reinforcement Learning With Transformers: The Development Trajectory","display_name":"On Transforming Reinforcement Learning With Transformers: The Development Trajectory","publication_year":2024,"publication_date":"2024-06-03","ids":{"openalex":"https://openalex.org/W4399310716","doi":"https://doi.org/10.1109/tpami.2024.3408271","pmid":"https://pubmed.ncbi.nlm.nih.gov/38829763"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2024.3408271","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3408271","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","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/A5084479881","display_name":"Shengchao Hu","orcid":"https://orcid.org/0000-0002-6860-2222"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengchao Hu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China","Shanghai Jiao Tong University and Shanghai AI Lab, China"],"raw_orcid":"https://orcid.org/0000-0002-6860-2222","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University and Shanghai AI Lab, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042802004","display_name":"Li Shen","orcid":"https://orcid.org/0000-0001-5659-3464"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Shen","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China","Sun Yat-sen University and JD Explore Academy, China"],"raw_orcid":"https://orcid.org/0000-0001-5659-3464","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"Sun Yat-sen University and JD Explore Academy, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100342828","display_name":"Ya Zhang","orcid":"https://orcid.org/0000-0002-5390-9053"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ya Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China","Shanghai Jiao Tong University and Shanghai AI Lab, China"],"raw_orcid":"https://orcid.org/0000-0002-5390-9053","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University and Shanghai AI Lab, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100393445","display_name":"Yixin Chen","orcid":"https://orcid.org/0000-0002-3704-4432"},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yixin Chen","raw_affiliation_strings":["Washington University in St Louis, St. Louis, MO, USA","Washington University in St Louis, America"],"raw_orcid":"https://orcid.org/0000-0002-3704-4432","affiliations":[{"raw_affiliation_string":"Washington University in St Louis, St. Louis, MO, USA","institution_ids":["https://openalex.org/I204465549"]},{"raw_affiliation_string":"Washington University in St Louis, America","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074103823","display_name":"Dacheng Tao","orcid":"https://orcid.org/0000-0001-7225-5449"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Dacheng Tao","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-7225-5449","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":15.5527,"has_fulltext":false,"cited_by_count":64,"citation_normalized_percentile":{"value":0.9927648,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"46","issue":"12","first_page":"8580","last_page":"8599"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9830999970436096,"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":0.9830999970436096,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7956669330596924},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7268737554550171},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7139037847518921},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5954039096832275},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5193882584571838},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4095512330532074},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18886014819145203},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.12654495239257812}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7956669330596924},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7268737554550171},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7139037847518921},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5954039096832275},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5193882584571838},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4095512330532074},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18886014819145203},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.12654495239257812},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2024.3408271","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3408271","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:38829763","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38829763","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 pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":198,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2114307208","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2158782408","https://openalex.org/W2168359464","https://openalex.org/W2169818249","https://openalex.org/W2413794162","https://openalex.org/W2423557781","https://openalex.org/W2799002257","https://openalex.org/W2805623918","https://openalex.org/W2810346659","https://openalex.org/W2902391430","https://openalex.org/W2962847657","https://openalex.org/W2963367210","https://openalex.org/W2963800628","https://openalex.org/W2964110616","https://openalex.org/W2967186499","https://openalex.org/W2970231061","https://openalex.org/W2970252402","https://openalex.org/W2970340522","https://openalex.org/W2970586934","https://openalex.org/W2973229164","https://openalex.org/W2979727876","https://openalex.org/W2987914945","https://openalex.org/W2997502221","https://openalex.org/W2998557583","https://openalex.org/W3009593063","https://openalex.org/W3011672202","https://openalex.org/W3025019304","https://openalex.org/W3034500398","https://openalex.org/W3034578524","https://openalex.org/W3034758614","https://openalex.org/W3035524453","https://openalex.org/W3035574168","https://openalex.org/W3038822267","https://openalex.org/W3109097593","https://openalex.org/W3127561923","https://openalex.org/W3138516171","https://openalex.org/W3152878473","https://openalex.org/W3156977692","https://openalex.org/W3172675210","https://openalex.org/W3172863135","https://openalex.org/W3175558129","https://openalex.org/W3191807689","https://openalex.org/W3199332348","https://openalex.org/W3200722893","https://openalex.org/W3208313084","https://openalex.org/W3208451383","https://openalex.org/W3209247505","https://openalex.org/W4200633542","https://openalex.org/W4206706211","https://openalex.org/W4206944021","https://openalex.org/W4213019189","https://openalex.org/W4214700710","https://openalex.org/W4226052928","https://openalex.org/W4226512186","https://openalex.org/W4283788970","https://openalex.org/W4287889738","https://openalex.org/W4287889972","https://openalex.org/W4312301659","https://openalex.org/W4312396550","https://openalex.org/W4312909062","https://openalex.org/W4360584316","https://openalex.org/W4365443922","https://openalex.org/W4383066231","https://openalex.org/W4385245566","https://openalex.org/W4386076400","https://openalex.org/W4389473504","https://openalex.org/W6637441126","https://openalex.org/W6637967152","https://openalex.org/W6640212811","https://openalex.org/W6679434410","https://openalex.org/W6680020707","https://openalex.org/W6692846177","https://openalex.org/W6735377749","https://openalex.org/W6736057607","https://openalex.org/W6741002519","https://openalex.org/W6745935785","https://openalex.org/W6747387971","https://openalex.org/W6747943641","https://openalex.org/W6748638692","https://openalex.org/W6749029207","https://openalex.org/W6750186571","https://openalex.org/W6752374788","https://openalex.org/W6755207826","https://openalex.org/W6755977528","https://openalex.org/W6757184387","https://openalex.org/W6757469721","https://openalex.org/W6757592117","https://openalex.org/W6758846586","https://openalex.org/W6760405395","https://openalex.org/W6763701032","https://openalex.org/W6764679822","https://openalex.org/W6765527290","https://openalex.org/W6766904570","https://openalex.org/W6768017362","https://openalex.org/W6768021236","https://openalex.org/W6768810269","https://openalex.org/W6768952226","https://openalex.org/W6769596995","https://openalex.org/W6769874972","https://openalex.org/W6770251742","https://openalex.org/W6770887232","https://openalex.org/W6771217966","https://openalex.org/W6771270455","https://openalex.org/W6771750343","https://openalex.org/W6772111244","https://openalex.org/W6772190580","https://openalex.org/W6772381481","https://openalex.org/W6774784542","https://openalex.org/W6776438516","https://openalex.org/W6776601253","https://openalex.org/W6778883912","https://openalex.org/W6779163011","https://openalex.org/W6779265984","https://openalex.org/W6779638344","https://openalex.org/W6779879114","https://openalex.org/W6780225908","https://openalex.org/W6780470247","https://openalex.org/W6780493881","https://openalex.org/W6781286002","https://openalex.org/W6782022165","https://openalex.org/W6783988234","https://openalex.org/W6784190712","https://openalex.org/W6784333009","https://openalex.org/W6784556858","https://openalex.org/W6785358402","https://openalex.org/W6786364697","https://openalex.org/W6789172296","https://openalex.org/W6789390734","https://openalex.org/W6790188114","https://openalex.org/W6790978476","https://openalex.org/W6791353385","https://openalex.org/W6795386847","https://openalex.org/W6796183756","https://openalex.org/W6796289742","https://openalex.org/W6796366729","https://openalex.org/W6796546720","https://openalex.org/W6798057236","https://openalex.org/W6798435993","https://openalex.org/W6798487212","https://openalex.org/W6799173934","https://openalex.org/W6800682094","https://openalex.org/W6800764332","https://openalex.org/W6800875267","https://openalex.org/W6802659552","https://openalex.org/W6802669662","https://openalex.org/W6802916882","https://openalex.org/W6803039797","https://openalex.org/W6803519892","https://openalex.org/W6804244202","https://openalex.org/W6804404469","https://openalex.org/W6804859080","https://openalex.org/W6809809871","https://openalex.org/W6810089409","https://openalex.org/W6810156098","https://openalex.org/W6810334672","https://openalex.org/W6810738896","https://openalex.org/W6810745647","https://openalex.org/W6811237044","https://openalex.org/W6838557027","https://openalex.org/W6838682728","https://openalex.org/W6838931476","https://openalex.org/W6838940190","https://openalex.org/W6838968580","https://openalex.org/W6839095836","https://openalex.org/W6839185451","https://openalex.org/W6839390831","https://openalex.org/W6839526036","https://openalex.org/W6839805037","https://openalex.org/W6840380725","https://openalex.org/W6840437412","https://openalex.org/W6841094356","https://openalex.org/W6842456838","https://openalex.org/W6842654171","https://openalex.org/W6842751340","https://openalex.org/W6846316339","https://openalex.org/W6846573952","https://openalex.org/W6846741855","https://openalex.org/W6847646427","https://openalex.org/W6848842611","https://openalex.org/W6849153783","https://openalex.org/W6849245622","https://openalex.org/W6849444386","https://openalex.org/W6849708121","https://openalex.org/W6850304935","https://openalex.org/W6852501889","https://openalex.org/W6852575923","https://openalex.org/W6853055758","https://openalex.org/W6854030435","https://openalex.org/W6854110918","https://openalex.org/W6856381720","https://openalex.org/W6857406036","https://openalex.org/W6857845051","https://openalex.org/W6859567472","https://openalex.org/W6862445342","https://openalex.org/W6866157721"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Transformers,":[0],"originally":[1],"devised":[2],"for":[3,30],"natural":[4],"language":[5],"processing":[6],"(NLP),":[7],"have":[8,37],"also":[9],"produced":[10],"significant":[11],"successes":[12],"in":[13,41,95,209,237],"computer":[14],"vision":[15],"(CV).":[16],"Due":[17],"to":[18,27,64,110,116,133,187,231],"their":[19,39],"strong":[20],"expression":[21],"power,":[22],"researchers":[23],"are":[24,141,185,211,219],"investigating":[25],"ways":[26],"deploy":[28],"transformers":[29,60],"reinforcement":[31],"learning":[32],"(RL),":[33],"and":[34,50,69,85,88,102,130,155,169,193,207,213,233],"transformer-based":[35],"models":[36],"manifested":[38],"potential":[40],"representative":[42],"RL":[43,58,62,117,122,136,150,163],"benchmarks.":[44],"In":[45],"this":[46,73,224,238],"paper,":[47],"we":[48],"collect":[49],"dissect":[51],"recent":[52],"advances":[53],"concerning":[54],"the":[55,66,77,90,112,120,145,156,179,196,205],"transformation":[56],"of":[57,72,93,128,148,200],"with":[59],"(transformer-based":[61],"(TRL))":[63],"explore":[65],"development":[67],"trajectory":[68,86],"future":[70,216,235],"trends":[71],"field.":[74,241],"We":[75,221],"group":[76],"existing":[78],"developments":[79],"into":[80],"two":[81],"categories:":[82],"architecture":[83],"enhancements":[84],"optimizations,":[87],"examine":[89],"main":[91],"applications":[92],"TRL":[94,210,232],"robotic":[96],"manipulation,":[97],"text-based":[98],"games":[99],"(TBGs),":[100],"navigation,":[101],"autonomous":[103],"driving.":[104],"Architecture":[105],"enhancement":[106],"methods":[107,140,161],"consider":[108],"how":[109],"apply":[111],"powerful":[113],"transformer":[114],"structure":[115],"problems":[118,164,168],"under":[119,178],"traditional":[121,134,149],"framework,":[123],"facilitating":[124],"more":[125],"precise":[126],"modeling":[127,167,198],"agents":[129],"environments":[131],"compared":[132],"deep":[135],"techniques.":[137],"However,":[138],"these":[139,203],"still":[142],"limited":[143],"by":[144],"inherent":[146],"defects":[147],"algorithms,":[151],"such":[152,183],"as":[153,165],"bootstrapping":[154],"\"deadly":[157],"triad\".":[158],"Trajectory":[159],"optimization":[160],"treat":[162],"sequence":[166],"train":[170],"a":[171,228],"joint":[172],"state-action":[173],"model":[174],"over":[175],"entire":[176],"trajectories":[177],"behavior":[180],"cloning":[181],"framework;":[182],"approaches":[184],"able":[186],"extract":[188],"policies":[189],"from":[190],"static":[191],"datasets":[192],"fully":[194],"use":[195],"long-sequence":[197],"capabilities":[199],"transformers.":[201],"Given":[202],"advancements,":[204],"limitations":[206],"challenges":[208],"reviewed":[212],"proposals":[214],"regarding":[215],"research":[217,236],"directions":[218],"discussed.":[220],"hope":[222],"that":[223],"survey":[225],"can":[226],"provide":[227],"detailed":[229],"introduction":[230],"motivate":[234],"rapidly":[239],"developing":[240]},"counts_by_year":[{"year":2026,"cited_by_count":18},{"year":2025,"cited_by_count":42},{"year":2024,"cited_by_count":4}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}