{"id":"https://openalex.org/W4413945492","doi":"https://doi.org/10.1109/icra55743.2025.11128715","title":"Goal-Guided Reinforcement Learning: Leveraging Large Language Models for Long-Horizon Task Decomposition","display_name":"Goal-Guided Reinforcement Learning: Leveraging Large Language Models for Long-Horizon Task Decomposition","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413945492","doi":"https://doi.org/10.1109/icra55743.2025.11128715"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11128715","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128715","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","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/A5084406689","display_name":"Ceng Zhang","orcid":"https://orcid.org/0009-0006-9456-4318"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Ceng Zhang","raw_affiliation_strings":["National University of Singapore,Department of Mechanical Engineering,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Mechanical Engineering,Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031855178","display_name":"Zhanhong Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhanhong Sun","raw_affiliation_strings":["National University of Singapore,Department of Mechanical Engineering,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Mechanical Engineering,Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012775344","display_name":"Gregory S. Chirikjian","orcid":"https://orcid.org/0000-0003-0542-9028"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Gregory S. Chirikjian","raw_affiliation_strings":["National University of Singapore,Department of Mechanical Engineering,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Mechanical Engineering,Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5084406689"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":4.2434,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.94997145,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"10744","last_page":"10750"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11122","display_name":"Online Learning and Analytics","score":0.8194000124931335,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11122","display_name":"Online Learning and Analytics","score":0.8194000124931335,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.777899980545044,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7432000041007996,"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":0.8696032762527466},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7617189288139343},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6847097277641296},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.6698011159896851},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49025967717170715},{"id":"https://openalex.org/keywords/horizon","display_name":"Horizon","score":0.485942006111145},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3688969016075134},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09154817461967468},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0588284432888031}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8696032762527466},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7617189288139343},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6847097277641296},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.6698011159896851},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49025967717170715},{"id":"https://openalex.org/C159176650","wikidata":"https://www.wikidata.org/wiki/Q43261","display_name":"Horizon","level":2,"score":0.485942006111145},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3688969016075134},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09154817461967468},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0588284432888031},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11128715","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128715","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6549065091","display_name":null,"funder_award_id":"A-0009428-08-00","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"}],"funders":[{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W2168359464","https://openalex.org/W2796290181","https://openalex.org/W2799002257","https://openalex.org/W2963523627","https://openalex.org/W4383097638","https://openalex.org/W4383108457","https://openalex.org/W4386499064","https://openalex.org/W4388660746","https://openalex.org/W4401023826","https://openalex.org/W4401415119","https://openalex.org/W4402890475","https://openalex.org/W4405910844"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W2366903352"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"has":[3],"long":[4],"struggled":[5],"with":[6,29,153],"exploration":[7],"in":[8],"vast":[9],"state-action":[10],"spaces,":[11],"particularly":[12],"for":[13,35,46],"intricate":[14],"tasks":[15,152],"that":[16,82,98],"necessitate":[17],"a":[18,78,95,100,105,112],"series":[19],"of":[20,86,142],"well-coordinated":[21],"actions.":[22],"Meanwhile,":[23],"large":[24],"language":[25],"models":[26],"(LLMs)":[27],"equipped":[28],"fundamental":[30],"knowledge":[31,61,85],"have":[32],"been":[33],"utilized":[34],"task":[36,57,107],"planning":[37],"across":[38,146],"various":[39],"domains.":[40],"However,":[41],"using":[42],"them":[43],"to":[44,88,103,115,133],"plan":[45],"long-term":[47],"objectives":[48],"can":[49,167],"be":[50,64,168],"demanding,":[51],"as":[52],"they":[53],"function":[54],"independently":[55],"from":[56,128],"environments":[58,149],"where":[59],"their":[60],"might":[62],"not":[63],"perfectly":[65],"aligned,":[66],"hence":[67],"often":[68],"overlooking":[69],"possible":[70],"physical":[71],"limitations.":[72],"To":[73],"this":[74],"end,":[75],"we":[76,162],"propose":[77],"goal-based":[79],"RL":[80,132],"framework":[81,145],"leverages":[83],"prior":[84],"LLMs":[87,129],"benefit":[89],"the":[90,121,125,131,140,143],"training":[91],"process.":[92],"We":[93,138],"introduce":[94],"hierarchical":[96],"module":[97],"features":[99],"goal":[101],"generator":[102],"segment":[104],"long-horizon":[106,151],"into":[108],"reachable":[109],"subgoals":[110],"and":[111,150,156,164],"policy":[113],"planner":[114],"generate":[116],"action":[117,157],"sequences":[118],"based":[119],"on":[120],"current":[122],"goal.":[123],"Subsequently,":[124],"policies":[126],"derived":[127],"guide":[130],"achieve":[134],"each":[135],"subgoal":[136],"sequentially.":[137],"validate":[139],"effectiveness":[141],"proposed":[144],"different":[147],"simulation":[148],"complex":[154],"state":[155],"spaces.":[158],"The":[159],"LLM":[160],"prompts":[161],"use":[163],"more":[165],"details":[166],"found":[169],"at":[170],"https://chirikjianlab.github.io/G2RL-LM/.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}
