{"id":"https://openalex.org/W4385764328","doi":"https://doi.org/10.24963/ijcai.2023/469","title":"Guide to Control: Offline Hierarchical Reinforcement Learning Using Subgoal Generation for Long-Horizon and Sparse-Reward Tasks","display_name":"Guide to Control: Offline Hierarchical Reinforcement Learning Using Subgoal Generation for Long-Horizon and Sparse-Reward Tasks","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385764328","doi":"https://doi.org/10.24963/ijcai.2023/469"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/469","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/469","pdf_url":"https://www.ijcai.org/proceedings/2023/0469.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0469.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108466371","display_name":"Won Chul Shin","orcid":"https://orcid.org/0000-0003-3044-9397"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Wonchul Shin","raw_affiliation_strings":["Sungkyunkwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sungkyunkwan University","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101688828","display_name":"Yusung Kim","orcid":"https://orcid.org/0000-0002-9306-8738"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yusung Kim","raw_affiliation_strings":["Sungkyunkwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sungkyunkwan University","institution_ids":["https://openalex.org/I848706"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3053,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.8425628,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4217","last_page":"4225"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9947999715805054,"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/T12288","display_name":"Optimization and Search Problems","score":0.9908000230789185,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8547518253326416},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.773210883140564},{"id":"https://openalex.org/keywords/offline-learning","display_name":"Offline learning","score":0.618442952632904},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5944022536277771},{"id":"https://openalex.org/keywords/online-and-offline","display_name":"Online and offline","score":0.5928654670715332},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5766686201095581},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5701885223388672},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5385082960128784},{"id":"https://openalex.org/keywords/horizon","display_name":"Horizon","score":0.5030388236045837},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4977986812591553},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.476644366979599},{"id":"https://openalex.org/keywords/online-learning","display_name":"Online learning","score":0.41115081310272217},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.13053998351097107}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8547518253326416},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.773210883140564},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.618442952632904},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5944022536277771},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.5928654670715332},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5766686201095581},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5701885223388672},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5385082960128784},{"id":"https://openalex.org/C159176650","wikidata":"https://www.wikidata.org/wiki/Q43261","display_name":"Horizon","level":2,"score":0.5030388236045837},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4977986812591553},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.476644366979599},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.41115081310272217},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.13053998351097107},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/469","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/469","pdf_url":"https://www.ijcai.org/proceedings/2023/0469.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/469","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/469","pdf_url":"https://www.ijcai.org/proceedings/2023/0469.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2191473729","display_name":null,"funder_award_id":"2019-0-00421","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G4296643599","display_name":null,"funder_award_id":"2022-0-01045","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G4700831490","display_name":null,"funder_award_id":"2022-","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G5080715506","display_name":null,"funder_award_id":"2019-0-00421","funder_id":"https://openalex.org/F4320321378","funder_display_name":"Sungkyunkwan University"},{"id":"https://openalex.org/G8874964841","display_name":null,"funder_award_id":"2019-0-00421","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"}],"funders":[{"id":"https://openalex.org/F4320321378","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20"},{"id":"https://openalex.org/F4320324891","display_name":"Iran Telecommunication Research Center","ror":"https://ror.org/01a3g2z22"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385764328.pdf"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W2257979135","https://openalex.org/W2904453761","https://openalex.org/W2920215304","https://openalex.org/W2949561945","https://openalex.org/W2950614095","https://openalex.org/W2978455699","https://openalex.org/W2985533531","https://openalex.org/W2991355586","https://openalex.org/W2993185773","https://openalex.org/W3016525976","https://openalex.org/W3031840745","https://openalex.org/W3033324992","https://openalex.org/W3122177264","https://openalex.org/W3122690883","https://openalex.org/W3123614573","https://openalex.org/W3128416529","https://openalex.org/W3177145475","https://openalex.org/W3190864623","https://openalex.org/W3205794883","https://openalex.org/W4221150639","https://openalex.org/W4226265259","https://openalex.org/W4281856560","https://openalex.org/W4287631403","https://openalex.org/W4287756699","https://openalex.org/W4300799055"],"related_works":["https://openalex.org/W4225619808","https://openalex.org/W4400438570","https://openalex.org/W4221145086","https://openalex.org/W4376223516","https://openalex.org/W4226221094","https://openalex.org/W4226042081","https://openalex.org/W4388926065","https://openalex.org/W4387293922","https://openalex.org/W4388482290","https://openalex.org/W3207447243"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,106],"(RL)":[2],"has":[3,32],"achieved":[4],"considerable":[5],"success":[6],"in":[7,148,169],"many":[8],"fields,":[9],"but":[10],"applying":[11],"it":[12,22],"to":[13,59,84,96,113,119],"real-world":[14],"problems":[15],"can":[16,62,80],"be":[17],"costly":[18],"and":[19,66,90,173],"risky":[20],"because":[21],"requires":[23],"a":[24,38,77,133],"lot":[25],"of":[26,36,105],"online":[27,45],"interaction.":[28,46],"Recently,":[29],"offline":[30,53,70,108,149,166],"RL":[31,55,150,167],"shown":[33],"the":[34,82,87,91,103,110,115,120],"possibility":[35],"extracting":[37],"solution":[39],"through":[40,131],"existing":[41],"logged":[42],"data":[43],"without":[44],"In":[47,102],"this":[48],"work,":[49],"we":[50],"propose":[51],"an":[52],"hierarchical":[54],"method,":[56],"Guider":[57,163],"(Guide":[58],"Control),":[60],"that":[61,79,125],"efficiently":[63],"solve":[64],"long-horizon":[65,170],"sparse-reward":[67],"tasks":[68,156],"from":[69,107],"data.":[71],"The":[72,138],"high-level":[73],"policy":[74,93,117],"sequentially":[75],"generates":[76],"subgoal":[78,127,135,140],"guide":[81],"agent":[83],"arrive":[85],"at":[86,181],"final":[88],"goal,":[89],"lower-level":[92],"learns":[94],"how":[95],"reach":[97],"each":[98],"given":[99],"guided":[100],"subgoal.":[101],"process":[104],"data,":[109],"key":[111],"is":[112,129,179],"make":[114],"low-level":[116],"reachable":[118],"generated":[121],"subgoals.":[122],"We":[123],"show":[124],"high-quality":[126],"generation":[128,141],"possible":[130],"pre-training":[132],"latent":[134],"prior":[136,165],"model.":[137],"well-regulated":[139],"improves":[142],"performance":[143],"while":[144],"avoiding":[145],"distributional":[146],"shifts":[147],"by":[151],"breaking":[152],"down":[153],"long,":[154],"complex":[155,174],"into":[157],"shorter,":[158],"easier":[159],"ones.":[160],"For":[161],"evaluations,":[162],"outperforms":[164],"methods":[168],"robot":[171],"navigation":[172],"manipulation":[175],"benchmarks.":[176],"Our":[177],"code":[178],"available":[180],"https://github.com/gckor/Guider.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}