{"id":"https://openalex.org/W4399418906","doi":"https://doi.org/10.1145/3651671.3651714","title":"Past Data-Driven Adaptation in Hierarchical Reinforcement Learning","display_name":"Past Data-Driven Adaptation in Hierarchical Reinforcement Learning","publication_year":2024,"publication_date":"2024-02-02","ids":{"openalex":"https://openalex.org/W4399418906","doi":"https://doi.org/10.1145/3651671.3651714"},"language":"en","primary_location":{"id":"doi:10.1145/3651671.3651714","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3651671.3651714","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 16th International Conference on Machine Learning and Computing","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/A5064660891","display_name":"Zhang Sijie","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Sijie Zhang","raw_affiliation_strings":["School of Computer Science & Engineering, University of Electronic Science and Technology of China: Chengdu, CN, China"],"raw_orcid":"https://orcid.org/0009-0007-2751-7607","affiliations":[{"raw_affiliation_string":"School of Computer Science & Engineering, University of Electronic Science and Technology of China: Chengdu, CN, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021348360","display_name":"Aiguo Chen","orcid":"https://orcid.org/0000-0002-3712-2349"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aiguo Chen","raw_affiliation_strings":["School of Computer Science & Engineering, University of Electronic Science and Technology of China: Chengdu, CN, China"],"raw_orcid":"https://orcid.org/0000-0002-3712-2349","affiliations":[{"raw_affiliation_string":"School of Computer Science & Engineering, University of Electronic Science and Technology of China: Chengdu, CN, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046514210","display_name":"Xincen Zhou","orcid":"https://orcid.org/0009-0005-5338-8648"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xincen Zhou","raw_affiliation_strings":["School of Computer Science & Engineering, University of Electronic Science and Technology of China: Chengdu, CN, China"],"raw_orcid":"https://orcid.org/0009-0005-5338-8648","affiliations":[{"raw_affiliation_string":"School of Computer Science & Engineering, University of Electronic Science and Technology of China: Chengdu, CN, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043537716","display_name":"Tianzi Wang","orcid":"https://orcid.org/0009-0004-1667-9190"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianzi Wang","raw_affiliation_strings":["School of Computer Science & Engineering, University of Electronic Science and Technology of China: Chengdu, CN, China"],"raw_orcid":"https://orcid.org/0009-0004-1667-9190","affiliations":[{"raw_affiliation_string":"School of Computer Science & Engineering, University of Electronic Science and Technology of China: Chengdu, CN, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5064660891"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06238922,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"29","last_page":"35"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980999827384949,"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":0.9980999827384949,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9890999794006348,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.982200026512146,"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":0.8551794290542603},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8336201906204224},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6654525995254517},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.6098470687866211},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5557926893234253},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5518362522125244},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5298854112625122},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.49598774313926697},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.4578898847103119},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4303813576698303},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.41027072072029114}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8551794290542603},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8336201906204224},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6654525995254517},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.6098470687866211},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5557926893234253},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5518362522125244},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5298854112625122},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.49598774313926697},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4578898847103119},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4303813576698303},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.41027072072029114},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3651671.3651714","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3651671.3651714","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 16th International Conference on Machine Learning and Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1556824961","https://openalex.org/W1578521162","https://openalex.org/W2090170171","https://openalex.org/W2964505566","https://openalex.org/W3012148463","https://openalex.org/W3184714257","https://openalex.org/W3208334305","https://openalex.org/W4212996499","https://openalex.org/W6634616096"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4323768008","https://openalex.org/W1941703695","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W4248382324","https://openalex.org/W2024136090","https://openalex.org/W3131574667"],"abstract_inverted_index":{"Reinforcement":[0,45],"learning":[1,68,87],"algorithms":[2],"struggle":[3],"with":[4,110],"tasks":[5,109],"that":[6,94],"have":[7],"complex":[8,111],"hierarchical":[9,112],"dependency":[10],"structures.":[11],"For":[12],"this":[13,32],"problem,":[14],"humans":[15],"usually":[16],"represent":[17],"the":[18,66,73,77,89],"whole":[19],"task":[20],"in":[21,43,108],"a":[22,36,53,61,82],"structured":[23],"way":[24],"and":[25,59,103],"solve":[26],"it":[27],"layer":[28],"by":[29],"layer.":[30],"In":[31],"paper,":[33],"we":[34],"propose":[35],"novel":[37],"approach":[38,96],"called":[39],"Past":[40],"Data-Driven":[41],"Adaptation":[42],"Hierarchical":[44],"Learning":[46],"(AdaHRL).":[47],"AdaHRL":[48,71],"leverages":[49],"\u2019past":[50],"samples\u2019":[51],"from":[52],"replay":[54,79,106],"buffer":[55,80],"to":[56],"discover":[57],"subgoals":[58],"construct":[60],"subgoal":[62],"tree,":[63],"effectively":[64],"steering":[65],"agent\u2019s":[67],"trajectory.":[69],"Simultaneously,":[70],"fine-tunes":[72],"data":[74],"distribution":[75],"of":[76],"entire":[78],"using":[81],"filter":[83],"function,":[84],"empowering":[85],"adaptive":[86],"within":[88],"agent.":[90],"Experimental":[91],"results":[92],"demonstrate":[93],"our":[95],"outperforms":[97],"Unified":[98],"Model-Free":[99],"HRL":[100],"Framework":[101],"(UHRL)":[102],"Hindsight":[104],"experience":[105],"(HER)":[107],"dependencies.":[113]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}