{"id":"https://openalex.org/W4389667622","doi":"https://doi.org/10.1109/iros55552.2023.10342230","title":"Hierarchical Decision Transformer","display_name":"Hierarchical Decision Transformer","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389667622","doi":"https://doi.org/10.1109/iros55552.2023.10342230"},"language":"en","primary_location":{"id":"doi:10.1109/iros55552.2023.10342230","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10342230","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 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/A5029312365","display_name":"Andr\u00e9 Correia","orcid":"https://orcid.org/0000-0002-0119-9790"},"institutions":[{"id":"https://openalex.org/I161321875","display_name":"University of Beira Interior","ror":"https://ror.org/03nf36p02","country_code":"PT","type":"education","lineage":["https://openalex.org/I161321875"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Andr\u00e9 Correia","raw_affiliation_strings":["NOVA LINCS, Universidade da Beira Interior, R. Marquês de Ávila e Bolama 6201–001,Covilhã,Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NOVA LINCS, Universidade da Beira Interior, R. Marquês de Ávila e Bolama 6201–001,Covilhã,Portugal","institution_ids":["https://openalex.org/I161321875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009791474","display_name":"Lu\u0131\u0301s A. Alexandre","orcid":"https://orcid.org/0000-0002-5133-5025"},"institutions":[{"id":"https://openalex.org/I161321875","display_name":"University of Beira Interior","ror":"https://ror.org/03nf36p02","country_code":"PT","type":"education","lineage":["https://openalex.org/I161321875"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Luis A. Alexandre","raw_affiliation_strings":["NOVA LINCS, Universidade da Beira Interior, R. Marquês de Ávila e Bolama 6201–001,Covilhã,Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NOVA LINCS, Universidade da Beira Interior, R. Marquês de Ávila e Bolama 6201–001,Covilhã,Portugal","institution_ids":["https://openalex.org/I161321875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5814,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.89905986,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1661","last_page":"1666"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9997000098228455,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9997000098228455,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9984999895095825,"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/T11023","display_name":"Prosthetics and Rehabilitation Robotics","score":0.9520999789237976,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8204284310340881},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7387645840644836},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7286583781242371},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6556336283683777},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5821089744567871},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5681577324867249},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4844639301300049},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1531129777431488},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.10451167821884155}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8204284310340881},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7387645840644836},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7286583781242371},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6556336283683777},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5821089744567871},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5681577324867249},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4844639301300049},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1531129777431488},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.10451167821884155},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros55552.2023.10342230","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10342230","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W368409423","https://openalex.org/W1931877416","https://openalex.org/W1986014385","https://openalex.org/W2883140436","https://openalex.org/W2950614095","https://openalex.org/W3016525976","https://openalex.org/W3035850588","https://openalex.org/W3039055967","https://openalex.org/W3090369311","https://openalex.org/W3169291081","https://openalex.org/W3175182975","https://openalex.org/W3184258323","https://openalex.org/W3187722890","https://openalex.org/W3212887262","https://openalex.org/W4287634727","https://openalex.org/W4288029578","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6752089545","https://openalex.org/W6767862010","https://openalex.org/W6779830607","https://openalex.org/W6780559895","https://openalex.org/W6784712800","https://openalex.org/W6796176593","https://openalex.org/W6796289742","https://openalex.org/W6797309367","https://openalex.org/W6797805403","https://openalex.org/W6799150178","https://openalex.org/W6801798027"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W20361778","https://openalex.org/W2024136090","https://openalex.org/W2964765435"],"abstract_inverted_index":{"Sequence":[0],"models":[1],"in":[2,35,58,92,104,119],"reinforcement":[3],"learning":[4,146],"require":[5],"task":[6,11,51,70,135,161],"knowledge":[7,52],"to":[8,41,77],"estimate":[9],"the":[10,16,30,59,65,69,75,82,117,138,141,156],"policy.":[12],"This":[13,79],"paper":[14],"presents":[15],"hierarchical":[17,24,142],"decision":[18],"transformer":[19,33],"(HDT).":[20],"HDT":[21],"is":[22],"a":[23,150,159,163],"behavior":[25],"cloning":[26],"algorithm":[27],"that":[28],"improves":[29],"performance":[31,89],"of":[32,84,107,123,127,140],"methods":[34],"imitation":[36],"learning,":[37],"improving":[38,87],"their":[39],"robustness":[40],"tasks":[42,93,106],"with":[43,94],"longer":[44,95],"episodes":[45,96],"and/or":[46],"sparse":[47],"rewards,":[48],"without":[49,133],"requiring":[50],"or":[53],"user":[54],"interaction":[55],"currently":[56],"present":[57],"state-of-the-art.":[60],"The":[61],"high-level":[62],"mechanism":[63],"guides":[64],"low-level":[66],"controller":[67],"through":[68],"by":[71],"selecting":[72],"sub-goals":[73],"for":[74,145],"latter":[76],"reach.":[78],"sequence":[80,151],"replaces":[81],"returns-to-go":[83],"previous":[85],"methods,":[86],"its":[88],"overall,":[90],"especially":[91],"and":[97,111,130],"scarcer":[98],"rewards.":[99],"We":[100,153],"validate":[101],"our":[102],"method":[103,115,157],"multiple":[105],"OpenAI":[108],"Gym,":[109],"D4RL,":[110],"RoboMimic":[112],"benchmarks.":[113],"Our":[114],"outperforms":[116],"baselines":[118],"twenty":[120],"three":[121],"out":[122],"thirty":[124],"one":[125],"settings":[126],"varied":[128],"horizons":[129],"reward":[131],"frequencies":[132],"prior":[134],"knowledge,":[136],"showing":[137],"advantages":[139],"model":[143],"approach":[144],"from":[147],"demonstrations":[148],"using":[149],"model.":[152],"also":[154],"evaluate":[155],"on":[158,162],"reaching":[160],"physical":[164],"robot.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}