{"id":"https://openalex.org/W4404576896","doi":"https://doi.org/10.1109/lra.2024.3504341","title":"QT-TDM: Planning With Transformer Dynamics Model and Autoregressive Q-Learning","display_name":"QT-TDM: Planning With Transformer Dynamics Model and Autoregressive Q-Learning","publication_year":2024,"publication_date":"2024-11-21","ids":{"openalex":"https://openalex.org/W4404576896","doi":"https://doi.org/10.1109/lra.2024.3504341"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2024.3504341","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lra.2024.3504341","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/lra.2024.3504341","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078075806","display_name":"Mostafa Kotb","orcid":null},"institutions":[{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Mostafa Kotb","raw_affiliation_strings":["Knowledge Technology Group, Department of Informatics, Universit&#x00E4;t Hamburg, Hamburg, Germany"],"raw_orcid":"https://orcid.org/0000-0002-4198-3889","affiliations":[{"raw_affiliation_string":"Knowledge Technology Group, Department of Informatics, Universit&#x00E4;t Hamburg, Hamburg, Germany","institution_ids":["https://openalex.org/I884043246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102025003","display_name":"Cornelius Weber","orcid":"https://orcid.org/0000-0001-5163-938X"},"institutions":[{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Cornelius Weber","raw_affiliation_strings":["Knowledge Technology Group, Department of Informatics, Universit&#x00E4;t Hamburg, Hamburg, Germany"],"raw_orcid":"https://orcid.org/0000-0001-5163-938X","affiliations":[{"raw_affiliation_string":"Knowledge Technology Group, Department of Informatics, Universit&#x00E4;t Hamburg, Hamburg, Germany","institution_ids":["https://openalex.org/I884043246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042086036","display_name":"Muhammad Burhan Hafez","orcid":"https://orcid.org/0000-0003-1670-8962"},"institutions":[{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Muhammad Burhan Hafez","raw_affiliation_strings":["School of Electronics and Computer Science, University of Southampton, Southampton, U.K","Hafez is with School of Electronics and Computer Science, University of Southampton, Southampton, U.K"],"raw_orcid":"https://orcid.org/0000-0003-1670-8962","affiliations":[{"raw_affiliation_string":"School of Electronics and Computer Science, University of Southampton, Southampton, U.K","institution_ids":["https://openalex.org/I43439940"]},{"raw_affiliation_string":"Hafez is with School of Electronics and Computer Science, University of Southampton, Southampton, U.K","institution_ids":["https://openalex.org/I43439940"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033486668","display_name":"Stefan Wermter","orcid":"https://orcid.org/0000-0003-1343-4775"},"institutions":[{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Wermter","raw_affiliation_strings":["Knowledge Technology Group, Department of Informatics, Universit&#x00E4;t Hamburg, Hamburg, Germany"],"raw_orcid":"https://orcid.org/0000-0003-1343-4775","affiliations":[{"raw_affiliation_string":"Knowledge Technology Group, Department of Informatics, Universit&#x00E4;t Hamburg, Hamburg, Germany","institution_ids":["https://openalex.org/I884043246"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5078075806"],"corresponding_institution_ids":["https://openalex.org/I884043246"],"apc_list":null,"apc_paid":null,"fwci":1.5747,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.84032419,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"10","issue":"1","first_page":"112","last_page":"119"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.6001999974250793,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.6001999974250793,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.5684000253677368,"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/T11159","display_name":"Manufacturing Process and Optimization","score":0.5577999949455261,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.7616044282913208},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5828068852424622},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.45371943712234497},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.23116019368171692},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.22379639744758606},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20290938019752502},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.13912883400917053},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.0607830286026001}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.7616044282913208},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5828068852424622},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45371943712234497},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.23116019368171692},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.22379639744758606},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20290938019752502},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.13912883400917053},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0607830286026001}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lra.2024.3504341","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lra.2024.3504341","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},{"id":"pmh:oai:eprints.soton.ac.uk:496195","is_oa":true,"landing_page_url":"http://doi.org/10.1109/LRA.2024.3504341>).","pdf_url":"https://eprints.soton.ac.uk/496195/1/QT_TDM_FINAL2-5.pdf","source":{"id":"https://openalex.org/S4306401019","display_name":"ePrints Soton (University of Southampton)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I43439940","host_organization_name":"University of Southampton","host_organization_lineage":["https://openalex.org/I43439940"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":{"id":"doi:10.1109/lra.2024.3504341","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lra.2024.3504341","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Climate action","id":"https://metadata.un.org/sdg/13","score":0.44999998807907104}],"awards":[{"id":"https://openalex.org/G6276684567","display_name":null,"funder_award_id":"TRR 169","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W2752796333","https://openalex.org/W2964110616","https://openalex.org/W3036619998","https://openalex.org/W3041202696","https://openalex.org/W3207342878","https://openalex.org/W4385245566","https://openalex.org/W4385473486","https://openalex.org/W4389666710","https://openalex.org/W6640963894","https://openalex.org/W6751494529","https://openalex.org/W6756256016","https://openalex.org/W6769596995","https://openalex.org/W6771217966","https://openalex.org/W6777635358","https://openalex.org/W6778000925","https://openalex.org/W6784333009","https://openalex.org/W6796289742","https://openalex.org/W6804244202","https://openalex.org/W6804859080","https://openalex.org/W6809990427","https://openalex.org/W6838557027","https://openalex.org/W6839256673","https://openalex.org/W6842654171","https://openalex.org/W6846146671","https://openalex.org/W6848588639","https://openalex.org/W6850503672","https://openalex.org/W6850540853","https://openalex.org/W6851800889","https://openalex.org/W6852501889","https://openalex.org/W6856810907","https://openalex.org/W6857720132","https://openalex.org/W6862538127"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2171218219","https://openalex.org/W1972271943","https://openalex.org/W2150410159","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345"],"abstract_inverted_index":{"Inspired":[0],"by":[1],"the":[2,5,17,28,38,75,108,116,126,134],"success":[3],"of":[4,19,40,120,128],"Transformer":[6,32],"architecture":[7],"in":[8,21,26,45,57,142,153],"natural":[9],"language":[10],"processing":[11],"and":[12,63,90,155,167],"computer":[13],"vision,":[14],"we":[15,83],"investigate":[16],"use":[18,84],"Transformers":[20,55,121],"Reinforcement":[22],"Learning":[23],"(RL),":[24],"specifically":[25],"modeling":[27],"environment's":[29,76],"dynamics":[30,123],"using":[31,96],"Dynamics":[33],"Models":[34],"(TDMs).":[35],"We":[36],"evaluate":[37],"capabilities":[39,119],"TDMs":[41],"for":[42,87],"continuous":[43,145],"control":[44,146],"real-time":[46,139],"planning":[47,69],"scenarios":[48],"with":[49,125,138],"Model":[50],"Predictive":[51],"Control":[52],"(MPC).":[53],"While":[54],"excel":[56],"long-horizon":[58],"prediction,":[59],"their":[60],"tokenization":[61],"mechanism":[62],"autoregressive":[64,93],"nature":[65],"lead":[66],"to":[67,102,132,159],"costly":[68],"over":[70],"long":[71],"horizons,":[72],"especially":[73],"as":[74,122],"dimensionality":[77],"increases.":[78],"To":[79],"alleviate":[80],"this":[81],"issue,":[82],"a":[85,97,104,129],"TDM":[86],"short-term":[88],"planning,":[89],"learn":[91],"an":[92],"discrete":[94],"Q-function":[95],"separate":[98],"Q-Transformer":[99,131],"(QT)":[100],"model":[101],"estimate":[103],"long-term":[105],"return":[106],"beyond":[107],"short-horizon":[109],"planning.":[110,140],"Our":[111],"proposed":[112],"method,":[113],"QT-TDM,":[114],"integrates":[115],"robust":[117],"predictive":[118],"models":[124,163],"efficacy":[127],"model-free":[130],"mitigate":[133],"computational":[135],"burden":[136],"associated":[137],"Experiments":[141],"diverse":[143],"state-based":[144],"tasks":[147],"show":[148],"that":[149],"QT-TDM":[150],"is":[151],"superior":[152],"performance":[154],"sample":[156],"efficiency":[157],"compared":[158],"existing":[160],"Transformer-based":[161],"RL":[162],"while":[164],"achieving":[165],"fast":[166],"computationally":[168],"efficient":[169],"inference.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-25T08:17:42.794288","created_date":"2025-10-10T00:00:00"}
