{"id":"https://openalex.org/W3208890675","doi":"https://doi.org/10.1109/tpami.2022.3192418","title":"Adjacency Constraint for Efficient Hierarchical Reinforcement Learning","display_name":"Adjacency Constraint for Efficient Hierarchical Reinforcement Learning","publication_year":2022,"publication_date":"2022-07-19","ids":{"openalex":"https://openalex.org/W3208890675","doi":"https://doi.org/10.1109/tpami.2022.3192418","mag":"3208890675","pmid":"https://pubmed.ncbi.nlm.nih.gov/35853052"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2022.3192418","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2022.3192418","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5026023372","display_name":"Tianren Zhang","orcid":"https://orcid.org/0000-0001-9687-5263"},"institutions":[{"id":"https://openalex.org/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianren Zhang","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China","Beijing Innovation Center for Future Chip, Beijing, China","LSBDPA Beijing Key Laboratory, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9687-5263","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Beijing Innovation Center for Future Chip, Beijing, China","institution_ids":["https://openalex.org/I4210165198"]},{"raw_affiliation_string":"LSBDPA Beijing Key Laboratory, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048321911","display_name":"Shangqi Guo","orcid":"https://orcid.org/0000-0003-3181-6881"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shangqi Guo","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3181-6881","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101667380","display_name":"Tian Tan","orcid":"https://orcid.org/0000-0001-9173-2984"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tian Tan","raw_affiliation_strings":["Department of Civil and Environmental Engineering, Stanford University, Stanford, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-9173-2984","affiliations":[{"raw_affiliation_string":"Department of Civil and Environmental Engineering, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004579631","display_name":"Xiaolin Hu","orcid":"https://orcid.org/0000-0002-4907-7354"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolin Hu","raw_affiliation_strings":["Department of Computer Science and Technology, Institute for Artificial Intelligence, Beijing National Research Center for Information Science and Technology, State Key Laboratory of Intelligent Technology and Systems, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4907-7354","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Institute for Artificial Intelligence, Beijing National Research Center for Information Science and Technology, State Key Laboratory of Intelligent Technology and Systems, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100352754","display_name":"Feng Chen","orcid":"https://orcid.org/0000-0003-4813-2494"},"institutions":[{"id":"https://openalex.org/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Chen","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China","LSBDPA Beijing Key Laboratory, Beijing, China","Beijing Innovation Center for Future Chip, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4813-2494","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"LSBDPA Beijing Key Laboratory, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Beijing Innovation Center for Future Chip, Beijing, China","institution_ids":["https://openalex.org/I4210165198"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5428,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.93464651,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"45","issue":"4","first_page":"4152","last_page":"4166"},"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9559000134468079,"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/T10639","display_name":"Advanced Software Engineering Methodologies","score":0.9067999720573425,"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/adjacency-list","display_name":"Adjacency list","score":0.8207980394363403},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8067836761474609},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.6825981140136719},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6400641202926636},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5887965559959412},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5322180986404419},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4915498197078705},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4594382643699646},{"id":"https://openalex.org/keywords/adjacency-matrix","display_name":"Adjacency matrix","score":0.4543135166168213},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.43830639123916626},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.4301607012748718},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4171743392944336},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3757326602935791},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33243972063064575},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.27528685331344604},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2613699734210968},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18950524926185608},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.08895376324653625}],"concepts":[{"id":"https://openalex.org/C110484373","wikidata":"https://www.wikidata.org/wiki/Q264398","display_name":"Adjacency list","level":2,"score":0.8207980394363403},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8067836761474609},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.6825981140136719},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6400641202926636},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5887965559959412},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5322180986404419},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4915498197078705},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4594382643699646},{"id":"https://openalex.org/C180356752","wikidata":"https://www.wikidata.org/wiki/Q727035","display_name":"Adjacency matrix","level":3,"score":0.4543135166168213},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.43830639123916626},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.4301607012748718},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4171743392944336},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3757326602935791},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33243972063064575},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.27528685331344604},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2613699734210968},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18950524926185608},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.08895376324653625},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2022.3192418","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2022.3192418","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:35853052","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35853052","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.49000000953674316,"display_name":"Peace, Justice and strong institutions"},{"id":"https://metadata.un.org/sdg/10","score":0.46000000834465027,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G3395539601","display_name":null,"funder_award_id":"2021ZD0200300","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5220867262","display_name":null,"funder_award_id":"62176133","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7861851748","display_name":"\u901a\u7528\u7c7b\u8111\u8ba1\u7b97\u67b6\u6784\u6a21\u578b\u4e0e\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61836004","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"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":103,"referenced_works":["https://openalex.org/W91815983","https://openalex.org/W567721252","https://openalex.org/W1585861384","https://openalex.org/W1591992921","https://openalex.org/W1592847719","https://openalex.org/W1850488217","https://openalex.org/W2056354534","https://openalex.org/W2090170171","https://openalex.org/W2109910161","https://openalex.org/W2119567691","https://openalex.org/W2138621090","https://openalex.org/W2143435603","https://openalex.org/W2158782408","https://openalex.org/W2160371091","https://openalex.org/W2417089653","https://openalex.org/W2752796333","https://openalex.org/W2753738274","https://openalex.org/W2767050701","https://openalex.org/W2769648743","https://openalex.org/W2789008106","https://openalex.org/W2803281228","https://openalex.org/W2908390575","https://openalex.org/W2911809292","https://openalex.org/W2920215304","https://openalex.org/W2949267040","https://openalex.org/W2962823158","https://openalex.org/W2963241167","https://openalex.org/W2963262099","https://openalex.org/W2963286043","https://openalex.org/W2963641140","https://openalex.org/W2963771109","https://openalex.org/W2963799213","https://openalex.org/W2963864421","https://openalex.org/W2963923407","https://openalex.org/W2964001908","https://openalex.org/W2964036701","https://openalex.org/W2964043796","https://openalex.org/W2964121744","https://openalex.org/W2964185768","https://openalex.org/W2970387978","https://openalex.org/W2970534317","https://openalex.org/W2970720334","https://openalex.org/W2970948392","https://openalex.org/W2970971581","https://openalex.org/W2976657239","https://openalex.org/W2995078345","https://openalex.org/W2997101648","https://openalex.org/W3002855444","https://openalex.org/W3018036994","https://openalex.org/W3020125231","https://openalex.org/W3034808834","https://openalex.org/W3101442004","https://openalex.org/W3103506774","https://openalex.org/W3115293622","https://openalex.org/W3129322645","https://openalex.org/W3136456184","https://openalex.org/W4213251304","https://openalex.org/W4252279978","https://openalex.org/W4293872189","https://openalex.org/W4297804343","https://openalex.org/W6616173779","https://openalex.org/W6631190155","https://openalex.org/W6634945376","https://openalex.org/W6635516443","https://openalex.org/W6639039794","https://openalex.org/W6680976742","https://openalex.org/W6683821272","https://openalex.org/W6684921986","https://openalex.org/W6692846177","https://openalex.org/W6703271639","https://openalex.org/W6704571135","https://openalex.org/W6716653466","https://openalex.org/W6734215269","https://openalex.org/W6735209194","https://openalex.org/W6736368053","https://openalex.org/W6737937804","https://openalex.org/W6740801417","https://openalex.org/W6746523204","https://openalex.org/W6748012927","https://openalex.org/W6748315105","https://openalex.org/W6748599296","https://openalex.org/W6748839928","https://openalex.org/W6748848655","https://openalex.org/W6752089545","https://openalex.org/W6753060773","https://openalex.org/W6754957883","https://openalex.org/W6755459604","https://openalex.org/W6755612348","https://openalex.org/W6757913983","https://openalex.org/W6758730483","https://openalex.org/W6759871227","https://openalex.org/W6762918752","https://openalex.org/W6763356705","https://openalex.org/W6764173040","https://openalex.org/W6766413688","https://openalex.org/W6766978945","https://openalex.org/W6767649332","https://openalex.org/W6767765287","https://openalex.org/W6768831546","https://openalex.org/W6779526804","https://openalex.org/W6779715229","https://openalex.org/W6781415338","https://openalex.org/W6802227391"],"related_works":["https://openalex.org/W4213150077","https://openalex.org/W2369410163","https://openalex.org/W2059018062","https://openalex.org/W2604585036","https://openalex.org/W2078477160","https://openalex.org/W1989103179","https://openalex.org/W1991172810","https://openalex.org/W125803343","https://openalex.org/W2117632582","https://openalex.org/W2153421018"],"abstract_inverted_index":{"Goal-conditioned":[0],"Hierarchical":[1],"Reinforcement":[2],"Learning":[3],"(HRL)":[4],"is":[5,34],"a":[6,38,77,94,111,118],"promising":[7],"approach":[8],"for":[9,44],"scaling":[10],"up":[11],"reinforcement":[12],"learning":[13],"(RL)":[14],"techniques.":[15],"However,":[16],"it":[17],"often":[18],"suffers":[19],"from":[20,71],"training":[21,139],"inefficiency":[22],"as":[23],"the":[24,28,31,67,72,82,100,105,114,124,170,175],"action":[25,69],"space":[26,41,70,75],"of":[27,81,177],"high-level,":[29],"i.e.,":[30],"goal":[32,40,74],"space,":[33],"large.":[35],"Searching":[36],"in":[37,93,110],"large":[39],"poses":[42],"difficulty":[43],"both":[45],"high-level":[46,68],"subgoal":[47],"generation":[48],"and":[49,148,155,164],"low-level":[50],"policy":[51],"learning.":[52],"In":[53],"this":[54,59,132],"article,":[55],"we":[56],"show":[57,130,167],"that":[58,92,131,143,168],"problem":[60],"can":[61,134,144],"be":[62,135],"effectively":[63],"alleviated":[64],"by":[65,123,138],"restricting":[66],"whole":[73],"to":[76],"k-step":[78],"adjacent":[79,147],"region":[80],"current":[83],"state":[84],"using":[85],"an":[86,140],"adjacency":[87,102,115,141,171],"constraint.":[88],"We":[89,128],"theoretically":[90],"prove":[91],"deterministic":[95],"Markov":[96],"Decision":[97],"Process":[98],"(MDP),":[99],"proposed":[101],"constraint":[103,116,133,172],"preserves":[104],"optimal":[106],"hierarchical":[107],"policy,":[108],"while":[109],"stochastic":[112],"MDP":[113],"induces":[117],"bounded":[119],"state-value":[120],"suboptimality":[121],"determined":[122],"MDP's":[125],"transition":[126],"structure.":[127],"further":[129],"practically":[136],"implemented":[137],"network":[142],"discriminate":[145],"between":[146],"non-adjacent":[149],"subgoals.":[150],"Experimental":[151],"results":[152],"on":[153],"discrete":[154],"continuous":[156],"control":[157],"tasks":[158,166],"including":[159],"challenging":[160],"simulated":[161],"robot":[162],"locomotion":[163],"manipulation":[165],"incorporating":[169],"significantly":[173],"boosts":[174],"performance":[176],"state-of-the-art":[178],"goal-conditioned":[179],"HRL":[180],"approaches.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}