{"id":"https://openalex.org/W4293518561","doi":"https://doi.org/10.1109/icme52920.2022.9859878","title":"Searching Latent Sub-Goals in Hierarchical Reinforcement Learning as Riemannian Manifold Optimization","display_name":"Searching Latent Sub-Goals in Hierarchical Reinforcement Learning as Riemannian Manifold Optimization","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4293518561","doi":"https://doi.org/10.1109/icme52920.2022.9859878"},"language":"en","primary_location":{"id":"doi:10.1109/icme52920.2022.9859878","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859878","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5030972033","display_name":"Sidun Liu","orcid":"https://orcid.org/0000-0001-7715-4698"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sidun Liu","raw_affiliation_strings":["National University of Defense Technology,Science and Technology on Parallel and Distributed Laboratory,Hunan,China","Science and Technology on Parallel and Distributed Laboratory, National University of Defense Technology, Hunan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Science and Technology on Parallel and Distributed Laboratory,Hunan,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"Science and Technology on Parallel and Distributed Laboratory, National University of Defense Technology, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018873974","display_name":"Peng Qiao","orcid":"https://orcid.org/0000-0002-7882-6449"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Qiao","raw_affiliation_strings":["National University of Defense Technology,Science and Technology on Parallel and Distributed Laboratory,Hunan,China","Science and Technology on Parallel and Distributed Laboratory, National University of Defense Technology, Hunan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Science and Technology on Parallel and Distributed Laboratory,Hunan,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"Science and Technology on Parallel and Distributed Laboratory, National University of Defense Technology, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051680867","display_name":"Yong Dou","orcid":"https://orcid.org/0000-0002-1256-8934"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Dou","raw_affiliation_strings":["National University of Defense Technology,Science and Technology on Parallel and Distributed Laboratory,Hunan,China","Science and Technology on Parallel and Distributed Laboratory, National University of Defense Technology, Hunan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Science and Technology on Parallel and Distributed Laboratory,Hunan,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"Science and Technology on Parallel and Distributed Laboratory, National University of Defense Technology, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102723856","display_name":"Ruochun Jin","orcid":"https://orcid.org/0000-0001-6217-4223"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruochun Jin","raw_affiliation_strings":["National University of Defense Technology,Science and Technology on Parallel and Distributed Laboratory,Hunan,China","Science and Technology on Parallel and Distributed Laboratory, National University of Defense Technology, Hunan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Science and Technology on Parallel and Distributed Laboratory,Hunan,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"Science and Technology on Parallel and Distributed Laboratory, National University of Defense Technology, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.3374,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.545177,"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":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9700999855995178,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9492999911308289,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/riemannian-manifold","display_name":"Riemannian manifold","score":0.6857632994651794},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6525448560714722},{"id":"https://openalex.org/keywords/manifold","display_name":"Manifold (fluid mechanics)","score":0.5960288047790527},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5496533513069153},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.502751350402832},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4616388976573944},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.40125471353530884},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3746753931045532},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.11370444297790527}],"concepts":[{"id":"https://openalex.org/C2779593128","wikidata":"https://www.wikidata.org/wiki/Q632814","display_name":"Riemannian manifold","level":2,"score":0.6857632994651794},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6525448560714722},{"id":"https://openalex.org/C529865628","wikidata":"https://www.wikidata.org/wiki/Q1790740","display_name":"Manifold (fluid mechanics)","level":2,"score":0.5960288047790527},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5496533513069153},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.502751350402832},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4616388976573944},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.40125471353530884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3746753931045532},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.11370444297790527},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme52920.2022.9859878","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859878","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G210572450","display_name":null,"funder_award_id":"61902415,61732018","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W567721252","https://openalex.org/W1923779967","https://openalex.org/W2109910161","https://openalex.org/W2158782408","https://openalex.org/W2160538589","https://openalex.org/W2580133360","https://openalex.org/W2787938642","https://openalex.org/W2798738034","https://openalex.org/W2947854252","https://openalex.org/W2949267040","https://openalex.org/W2949604932","https://openalex.org/W2950614095","https://openalex.org/W2952372843","https://openalex.org/W2997701990","https://openalex.org/W3014571813","https://openalex.org/W3032398409","https://openalex.org/W3035037263","https://openalex.org/W3036125317","https://openalex.org/W3103296069","https://openalex.org/W4289441014","https://openalex.org/W4295521014","https://openalex.org/W4300799055","https://openalex.org/W4320013936","https://openalex.org/W6616173779","https://openalex.org/W6640156344","https://openalex.org/W6675747103","https://openalex.org/W6683455520","https://openalex.org/W6729295261","https://openalex.org/W6734215269","https://openalex.org/W6735913928","https://openalex.org/W6740801417","https://openalex.org/W6748839928","https://openalex.org/W6752089545","https://openalex.org/W6755459604","https://openalex.org/W6759871227","https://openalex.org/W6778875248","https://openalex.org/W6779715229"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2546668543","https://openalex.org/W2952208990"],"abstract_inverted_index":{"Hierarchical":[0],"Reinforcement":[1],"Learning":[2],"(HRL)":[3],"is":[4,36,41,59,167],"promising":[5],"to":[6,74],"tackle":[7],"the":[8,19,33,55,63,76,88,98,103,107,123,130,142,155,160,164],"long-term":[9],"sparse":[10],"reward":[11],"problem.":[12],"However,":[13],"goal":[14,20],"conditioned":[15],"HRL,":[16],"which":[17],"decomposes":[18],"into":[21],"a":[22,45,80,83,113],"series":[23,114],"of":[24,65,70,105,115,163],"sub-goals,":[25],"suffers":[26],"from":[27],"sub-goal":[28,66],"search":[29],"inefficiency":[30],"problems":[31],"when":[32],"observation":[34,47,120],"space":[35,78],"too":[37],"large.":[38],"This":[39],"problem":[40],"more":[42],"severe":[43],"in":[44,97,137],"visual":[46,119],"space,":[48,101,140],"since":[49],"its":[50],"high":[51],"latent":[52,77,100,139],"dimensions,":[53],"where":[54,154],"complete":[56],"dynamics":[57,108],"information":[58,109],"preserved,":[60],"exponentially":[61],"increase":[62],"difficulty":[64],"search.":[67],"In":[68,150],"view":[69],"this,":[71],"we":[72],"propose":[73],"treat":[75],"as":[79],"manifold,":[81],"i.e.,":[82],"Riemannian":[84,89,125],"manifold.":[85],"Assisted":[86],"by":[87,145],"manifold":[90,126],"optimization,":[91,127],"sub-goals":[92,136],"can":[93],"be":[94],"efficiently":[95],"searched":[96],"higher-dimensional":[99],"with":[102,118,129],"help":[104],"preserving":[106],"efficiently.":[110],"Experiments":[111],"on":[112,148],"MuJoCo":[116],"tasks":[117],"show":[121],"that":[122,132],"proposed":[124,165],"compared":[128],"baseline":[131,156],"directly":[133],"searches":[134],"for":[135],"bounded":[138],"improves":[141],"success":[143,161],"rate":[144,162],"1.5":[146],"times":[147],"average.":[149],"much":[151],"higher":[152],"dimensions":[153],"no":[157],"longer":[158],"converges,":[159],"method":[166],"maintained.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}