{"id":"https://openalex.org/W4405778674","doi":"https://doi.org/10.1109/iros58592.2024.10801303","title":"Steering Decision Transformers via Temporal Difference Learning","display_name":"Steering Decision Transformers via Temporal Difference Learning","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405778674","doi":"https://doi.org/10.1109/iros58592.2024.10801303"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10801303","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801303","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-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/A5086145215","display_name":"Hao-Lun Hsu","orcid":null},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hao-Lun Hsu","raw_affiliation_strings":["Duke University,Department of Computer Science,Durham,NC,USA,27708"],"affiliations":[{"raw_affiliation_string":"Duke University,Department of Computer Science,Durham,NC,USA,27708","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083621014","display_name":"Alper Kamil Bozkurt","orcid":"https://orcid.org/0000-0001-5845-4003"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alper Kamil Bozkurt","raw_affiliation_strings":["Duke University,Department of Computer Science,Durham,NC,USA,27708"],"affiliations":[{"raw_affiliation_string":"Duke University,Department of Computer Science,Durham,NC,USA,27708","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031584101","display_name":"Juncheng Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juncheng Dong","raw_affiliation_strings":["Duke University,Department of Electrical and Computer Engineering,Durham,NC,USA,27708"],"affiliations":[{"raw_affiliation_string":"Duke University,Department of Electrical and Computer Engineering,Durham,NC,USA,27708","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076201548","display_name":"Qitong Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qitong Gao","raw_affiliation_strings":["Duke University,Department of Electrical and Computer Engineering,Durham,NC,USA,27708"],"affiliations":[{"raw_affiliation_string":"Duke University,Department of Electrical and Computer Engineering,Durham,NC,USA,27708","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020766546","display_name":"Vahid Tarokh","orcid":"https://orcid.org/0000-0003-2994-6302"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vahid Tarokh","raw_affiliation_strings":["Duke University,Department of Electrical and Computer Engineering,Durham,NC,USA,27708"],"affiliations":[{"raw_affiliation_string":"Duke University,Department of Electrical and Computer Engineering,Durham,NC,USA,27708","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086742584","display_name":"Miroslav Paji\u0107","orcid":"https://orcid.org/0000-0002-5357-0117"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Miroslav Pajic","raw_affiliation_strings":["Duke University,Department of Electrical and Computer Engineering,Durham,NC,USA,27708"],"affiliations":[{"raw_affiliation_string":"Duke University,Department of Electrical and Computer Engineering,Durham,NC,USA,27708","institution_ids":["https://openalex.org/I170897317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5086145215"],"corresponding_institution_ids":["https://openalex.org/I170897317"],"apc_list":null,"apc_paid":null,"fwci":1.3476,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.83503421,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"7477","last_page":"7483"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10525","display_name":"Human-Automation Interaction and Safety","score":0.9108999967575073,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social 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/T10525","display_name":"Human-Automation Interaction and Safety","score":0.9108999967575073,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6265172362327576},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5383577942848206},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3567129373550415},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.23609167337417603},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.15128427743911743},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.06053042411804199}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6265172362327576},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5383577942848206},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3567129373550415},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.23609167337417603},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.15128427743911743},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.06053042411804199}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10801303","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801303","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1977655452","https://openalex.org/W2962894046","https://openalex.org/W3009593063","https://openalex.org/W4205280756","https://openalex.org/W4383097427","https://openalex.org/W4383108222","https://openalex.org/W4385430679","https://openalex.org/W4385438620","https://openalex.org/W4389667572","https://openalex.org/W4390872260","https://openalex.org/W4393159693","https://openalex.org/W4405778674","https://openalex.org/W6637967152","https://openalex.org/W6640963894","https://openalex.org/W6683195989","https://openalex.org/W6765008394","https://openalex.org/W6769609827","https://openalex.org/W6776438516","https://openalex.org/W6776601253","https://openalex.org/W6779265984","https://openalex.org/W6779463497","https://openalex.org/W6785353143","https://openalex.org/W6796289742","https://openalex.org/W6802659552","https://openalex.org/W6804244202","https://openalex.org/W6810473782","https://openalex.org/W6838356327","https://openalex.org/W6839185451","https://openalex.org/W6840437412","https://openalex.org/W6842456838","https://openalex.org/W6846741855","https://openalex.org/W6854030435","https://openalex.org/W6856810907","https://openalex.org/W6857018219"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Decision":[0],"Transformers":[1],"(DTs)":[2],"have":[3,117],"been":[4],"highly":[5],"effective":[6],"for":[7,114],"offline":[8,133],"reinforcement":[9],"learning":[10],"(RL)":[11],"tasks,":[12],"successfully":[13],"modeling":[14],"the":[15,45,53,58,68,90,105,112],"sequences":[16],"of":[17,23,48,56],"actions":[18],"in":[19,30,36,136],"a":[20],"given":[21],"set":[22],"demonstrations.":[24],"However,":[25],"DTs":[26,62,79,115],"may":[27],"perform":[28],"poorly":[29],"stochastic":[31],"environments,":[32],"which":[33],"are":[34,93],"prevalent":[35],"robotics":[37],"scenarios.":[38],"In":[39],"this":[40,49,72],"paper,":[41],"we":[42,74,101],"identify":[43],"that":[44,80,128],"root":[46],"cause":[47],"performance":[50],"degradation":[51],"is":[52],"growing":[54,106],"variance":[55,107],"returns-to-go,":[57],"signal":[59],"used":[60],"by":[61],"to":[63,78,83,116,119],"predict":[64],"actions,":[65],"accumulated":[66],"over":[67],"horizon.":[69],"Building":[70],"upon":[71],"insight,":[73],"propose":[75],"an":[76],"extension":[77],"allows":[81],"them":[82],"be":[84],"steered":[85],"toward":[86],"high-reward":[87],"regions,":[88],"where":[89],"expected":[91],"returns":[92],"estimated":[94],"using":[95],"temporal":[96],"difference":[97],"learning.":[98],"This":[99],"way,":[100],"not":[102],"only":[103],"mitigate":[104],"problem":[108],"but":[109],"also":[110],"eliminate":[111],"need":[113],"access":[118],"returns-to-go":[120],"during":[121],"evaluation":[122],"and":[123,139],"deployment":[124],"phases.":[125],"We":[126],"show":[127],"our":[129],"method":[130],"outperforms":[131],"state-of-the-art":[132],"RL":[134],"methods":[135],"both":[137],"simulated":[138],"real-world":[140],"robotic":[141],"arm":[142],"environments.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}