{"id":"https://openalex.org/W7142575183","doi":null,"title":"Efficient Exploitation of Hierarchical Structure in Sparse Reward Reinforcement Learning","display_name":"Efficient Exploitation of Hierarchical Structure in Sparse Reward Reinforcement Learning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W7142575183"},"language":"en","primary_location":{"id":"pmh:oai:re.public.polimi.it:11311/1310554","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/11311/1310554","pdf_url":null,"source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"parent_works":[],"lineage":["https://openalex.org/W7142575183"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/11311/1310554","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088578493","display_name":"Gianluca Drappo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Drappo G.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130823878","display_name":"Robert A.","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Robert A.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017130830","display_name":"Marcello Restelli","orcid":"https://orcid.org/0000-0002-6322-1076","observed_orcids":["https://orcid.org/0000-0002-6322-1076"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Restelli M.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060700722","display_name":"A. Aldo Faisal","orcid":"https://orcid.org/0000-0003-0813-7207","observed_orcids":["https://orcid.org/0000-0003-0813-7207"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Faisal A. A.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037963323","display_name":"Alberto Maria Metelli","orcid":"https://orcid.org/0000-0002-3424-5212","observed_orcids":["https://orcid.org/0000-0002-3424-5212"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Metelli A. M.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130863316","display_name":"Pike-Burke C.","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pike-Burke C.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10906","display_name":"AI-based Problem Solving and Planning","score":0.0,"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/hierarchical-reinforcement-learning","display_name":"hierarchical reinforcement learning","score":0.9850000143051147},{"id":"https://openalex.org/keywords/sparse-rewards","display_name":"sparse rewards","score":0.734000027179718},{"id":"https://openalex.org/keywords/hierarchical-decomposition","display_name":"hierarchical decomposition","score":0.8309999704360962},{"id":"https://openalex.org/keywords/regret-bounds","display_name":"regret bounds","score":0.9210000038146973}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.8222000002861023},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6967999935150146},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6581000089645386},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5842999815940857},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.5699999928474426},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.46650001406669617},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.460099995136261},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4577000141143799},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.4277999997138977},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4027999937534332},{"id":"https://openalex.org/C124527596","wikidata":"https://www.wikidata.org/wiki/Q17029359","display_name":"Hierarchical control system","level":3,"score":0.3691999912261963},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3479999899864197},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.319599986076355},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29809999465942383},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2858999967575073},{"id":"https://openalex.org/C3018263672","wikidata":"https://www.wikidata.org/wiki/Q1296251","display_name":"Efficient algorithm","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C53059260","wikidata":"https://www.wikidata.org/wiki/Q374758","display_name":"Multilevel model","level":2,"score":0.25780001282691956}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:re.public.polimi.it:11311/1310554","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/11311/1310554","pdf_url":null,"source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:spiral.imperial.ac.uk:10044/1/118404","doi":null,"is_oa":false,"landing_page_url":"https://hdl.handle.net/10044/1/118404","pdf_url":null,"source":{"id":"https://openalex.org/S4306401396","display_name":"Spiral (Imperial College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I47508984","host_organization_name":"Imperial College London","host_organization_lineage":["https://openalex.org/I47508984"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2269","raw_type":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai:re.public.polimi.it:11311/1310554","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/11311/1310554","pdf_url":null,"source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7133194230","https://openalex.org/W7172245025","https://openalex.org/W4391454473","https://openalex.org/W2945263287","https://openalex.org/W3139474403","https://openalex.org/W7210270636","https://openalex.org/W112321980","https://openalex.org/W4225884757","https://openalex.org/W7095489022","https://openalex.org/W4401507809"],"abstract_inverted_index":{"We":[0,60,116],"study":[1],"goal-conditioned":[2],"Hierarchical":[3],"Reinforcement":[4],"Learning":[5],"(HRL),":[6],"where":[7],"a":[8,14,21,31,42,54,76,81],"high-level":[9],"agent":[10],"instructs":[11],"sub-goals":[12],"to":[13,34,51,85],"low-level":[15,43,58,65],"agent.":[16],"Under":[17],"the":[18,64,99,112,133],"assumption":[19],"of":[20,57,98],"sparse":[22],"reward":[23],"function":[24],"and":[25,47,69],"known":[26],"hierarchical":[27,37,100,106,134],"decomposition,":[28],"we":[29],"propose":[30],"new":[32],"algorithm":[33,40,74,107],"learn":[35],"optimal":[36],"policies.":[38,59],"Our":[39],"takes":[41],"policy":[44,66],"as":[45],"input":[46],"is":[48,67,108],"flexible":[49],"enough":[50],"work":[52],"with":[53,121],"wide":[55],"range":[56],"show":[61],"that":[62,102,104,123,125,131],"when":[63],"optimistic":[68],"provably":[70],"efficient,":[71],"our":[72,91,105,118,126],"HRL":[73],"enjoys":[75],"regret":[77,92],"bound":[78,94],"which":[79],"represents":[80],"significant":[82],"improvement":[83],"compared":[84],"previous":[86],"results":[87],"for":[88],"HRL.":[89],"Importantly,":[90],"upper":[93],"highlights":[95],"key":[96],"characteristics":[97],"decomposition":[101],"guarantee":[103],"more":[109],"efficient":[110],"than":[111],"best":[113],"monolithic":[114],"approach.":[115],"support":[117],"theoretical":[119],"findings":[120],"experiments":[122],"underscore":[124],"method":[127],"consistently":[128],"outperforms":[129],"algorithms":[130],"ignore":[132],"structure.":[135]},"counts_by_year":[],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2026-03-29T00:00:00"}