{"id":"https://openalex.org/W4410636851","doi":"https://doi.org/10.1145/3701716.3715233","title":"Hierarchical Prompt Decision Transformer: Improving Few-Shot Policy Generalization with Global and Adaptive Guidance","display_name":"Hierarchical Prompt Decision Transformer: Improving Few-Shot Policy Generalization with Global and Adaptive Guidance","publication_year":2025,"publication_date":"2025-05-08","ids":{"openalex":"https://openalex.org/W4410636851","doi":"https://doi.org/10.1145/3701716.3715233"},"language":"en","primary_location":{"id":"doi:10.1145/3701716.3715233","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3715233","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3715233","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3715233","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zhe Wang","orcid":"https://orcid.org/0009-0008-3444-5872"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhe Wang","raw_affiliation_strings":["University of Virginia, Charlottesville, Virginia, USA"],"raw_orcid":"https://orcid.org/0009-0008-3444-5872","affiliations":[{"raw_affiliation_string":"University of Virginia, Charlottesville, Virginia, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076722448","display_name":"Haozhu Wang","orcid":"https://orcid.org/0000-0002-9679-0144"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haozhu Wang","raw_affiliation_strings":["Amazon, Santa Clara, California, USA"],"raw_orcid":"https://orcid.org/0000-0002-9679-0144","affiliations":[{"raw_affiliation_string":"Amazon, Santa Clara, California, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101887931","display_name":"Yanjun Qi","orcid":"https://orcid.org/0000-0002-5796-7453"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanjun Qi","raw_affiliation_strings":["Amazon, Arlington, Virginia, USA"],"raw_orcid":"https://orcid.org/0000-0002-5796-7453","affiliations":[{"raw_affiliation_string":"Amazon, Arlington, Virginia, USA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"520","last_page":"529"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9979000091552734,"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":0.9979000091552734,"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/generalization","display_name":"Generalization","score":0.6963692307472229},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6598922610282898},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5825244188308716},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.48984381556510925},{"id":"https://openalex.org/keywords/one-shot","display_name":"One shot","score":0.42954856157302856},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42917120456695557},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16475266218185425},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12971463799476624},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.07077649235725403}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6963692307472229},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6598922610282898},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5825244188308716},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.48984381556510925},{"id":"https://openalex.org/C2992734406","wikidata":"https://www.wikidata.org/wiki/Q413267","display_name":"One shot","level":2,"score":0.42954856157302856},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42917120456695557},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16475266218185425},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12971463799476624},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.07077649235725403},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3701716.3715233","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3715233","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3715233","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3701716.3715233","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3715233","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3715233","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410636851.pdf","grobid_xml":"https://content.openalex.org/works/W4410636851.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W2158782408","https://openalex.org/W2990138404","https://openalex.org/W3027879771","https://openalex.org/W3106539628","https://openalex.org/W3169291081","https://openalex.org/W4205991051","https://openalex.org/W4214717370","https://openalex.org/W4281965936","https://openalex.org/W4283205689","https://openalex.org/W4310390787","https://openalex.org/W4312245858","https://openalex.org/W4389667622","https://openalex.org/W6771876938","https://openalex.org/W6884300163"],"related_works":["https://openalex.org/W2497720472","https://openalex.org/W4292659306","https://openalex.org/W3044321615","https://openalex.org/W2806221744","https://openalex.org/W2326937258","https://openalex.org/W394267150","https://openalex.org/W2773965352","https://openalex.org/W4294892107","https://openalex.org/W2357748469","https://openalex.org/W2392917037"],"abstract_inverted_index":{"Decision":[0],"transformers":[1,37,143],"recast":[2],"reinforcement":[3],"learning":[4],"as":[5,81],"a":[6,12,65,108],"conditional":[7],"sequence":[8],"generation":[9],"problem,":[10],"offering":[11],"simple":[13],"but":[14],"effective":[15,146],"alternative":[16],"to":[17,38,51,57,148],"traditional":[18],"value":[19],"or":[20],"policy-based":[21],"methods.":[22],"A":[23],"recent":[24],"key":[25],"development":[26],"in":[27,35,122],"this":[28],"area":[29],"is":[30,144],"the":[31,123,129],"integration":[32],"of":[33,78,111],"prompting":[34,67,140],"decision":[36,142],"facilitate":[39],"few-shot":[40,150],"policy":[41,151],"generalization.":[42,152],"However,":[43],"current":[44],"methods":[45],"mainly":[46],"use":[47],"static":[48],"prompt":[49],"segments":[50],"guide":[52],"rollouts,":[53],"limiting":[54],"their":[55],"ability":[56],"provide":[58],"context-specific":[59],"guidance.":[60,116],"Addressing":[61],"this,":[62],"we":[63],"introduce":[64],"hierarchical":[66,139],"approach":[68,131],"enabled":[69],"by":[70],"retrieval":[71],"augmentation.":[72],"Our":[73],"method":[74],"learns":[75],"two":[76],"layers":[77],"soft":[79],"tokens":[80,86,95,103],"guiding":[82],"prompts:":[83],"(1)":[84],"global":[85],"encapsulating":[87],"task-level":[88],"information":[89],"about":[90],"trajectories,":[91],"and":[92,125],"(2)":[93],"adaptive":[94,102],"that":[96,138],"deliver":[97],"focused,":[98],"timestep-specific":[99],"instructions.":[100],"The":[101],"are":[104],"dynamically":[105],"retrieved":[106],"from":[107],"curated":[109],"set":[110],"demonstration":[112],"segments,":[113],"ensuring":[114],"context-aware":[115],"Experiments":[117],"across":[118],"seven":[119],"benchmark":[120],"tasks":[121],"MuJoCo":[124],"MetaWorld":[126],"environments":[127],"demonstrate":[128],"proposed":[130],"consistently":[132],"outperforms":[133],"all":[134],"baseline":[135],"methods,":[136],"suggesting":[137],"for":[141],"an":[145],"strategy":[147],"enable":[149]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}