{"id":"https://openalex.org/W4415452640","doi":"https://doi.org/10.3390/make7040126","title":"Large Language Models for Structured Task Decomposition in Reinforcement Learning Problems with Sparse Rewards","display_name":"Large Language Models for Structured Task Decomposition in Reinforcement Learning Problems with Sparse Rewards","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4415452640","doi":"https://doi.org/10.3390/make7040126"},"language":"en","primary_location":{"id":"doi:10.3390/make7040126","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make7040126","pdf_url":"https://www.mdpi.com/2504-4990/7/4/126/pdf?version=1761140806","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2504-4990/7/4/126/pdf?version=1761140806","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114285455","display_name":"Unai Ruiz-Gonzalez","orcid":"https://orcid.org/0009-0006-2536-5964"},"institutions":[{"id":"https://openalex.org/I4210124459","display_name":"Association of Electronic and Information Technologies","ror":"https://ror.org/02trgdk48","country_code":"ES","type":"other","lineage":["https://openalex.org/I4210124459"]},{"id":"https://openalex.org/I169108374","display_name":"University of the Basque Country","ror":"https://ror.org/000xsnr85","country_code":"ES","type":"education","lineage":["https://openalex.org/I169108374"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Unai Ruiz-Gonzalez","raw_affiliation_strings":["Department of Communications Engineering, University of the Basque Country (UPV/EHU), 48013 Bilbao, Spain","TECNALIA, Basque Research and Technology Alliance (BRTA), 48160 Derio, Spain"],"affiliations":[{"raw_affiliation_string":"Department of Communications Engineering, University of the Basque Country (UPV/EHU), 48013 Bilbao, Spain","institution_ids":["https://openalex.org/I169108374"]},{"raw_affiliation_string":"TECNALIA, Basque Research and Technology Alliance (BRTA), 48160 Derio, Spain","institution_ids":["https://openalex.org/I4210124459"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082466907","display_name":"Alain Andr\u00e9s","orcid":"https://orcid.org/0000-0002-4688-1304"},"institutions":[{"id":"https://openalex.org/I4210124459","display_name":"Association of Electronic and Information Technologies","ror":"https://ror.org/02trgdk48","country_code":"ES","type":"other","lineage":["https://openalex.org/I4210124459"]},{"id":"https://openalex.org/I136040515","display_name":"Universidad de Deusto","ror":"https://ror.org/00ne6sr39","country_code":"ES","type":"education","lineage":["https://openalex.org/I136040515"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Alain Andres","raw_affiliation_strings":["Faculty of Engineering, University of Deusto, 20012 Donostia, Spain","TECNALIA, Basque Research and Technology Alliance (BRTA), 48160 Derio, Spain"],"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, University of Deusto, 20012 Donostia, Spain","institution_ids":["https://openalex.org/I136040515"]},{"raw_affiliation_string":"TECNALIA, Basque Research and Technology Alliance (BRTA), 48160 Derio, Spain","institution_ids":["https://openalex.org/I4210124459"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017326471","display_name":"Javier Del Ser","orcid":"https://orcid.org/0000-0002-1260-9775"},"institutions":[{"id":"https://openalex.org/I4210124459","display_name":"Association of Electronic and Information Technologies","ror":"https://ror.org/02trgdk48","country_code":"ES","type":"other","lineage":["https://openalex.org/I4210124459"]},{"id":"https://openalex.org/I169108374","display_name":"University of the Basque Country","ror":"https://ror.org/000xsnr85","country_code":"ES","type":"education","lineage":["https://openalex.org/I169108374"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Javier Del Ser","raw_affiliation_strings":["Department of Mathematics, University of the Basque Country (UPV/EHU), 48940 Leioa, Spain","TECNALIA, Basque Research and Technology Alliance (BRTA), 48160 Derio, Spain"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics, University of the Basque Country (UPV/EHU), 48940 Leioa, Spain","institution_ids":["https://openalex.org/I169108374"]},{"raw_affiliation_string":"TECNALIA, Basque Research and Technology Alliance (BRTA), 48160 Derio, Spain","institution_ids":["https://openalex.org/I4210124459"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5017326471","https://openalex.org/A5114285455"],"corresponding_institution_ids":["https://openalex.org/I169108374","https://openalex.org/I4210124459"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16786697,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"7","issue":"4","first_page":"126","last_page":"126"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9282000064849854,"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":0.9282000064849854,"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/supervisor","display_name":"Supervisor","score":0.7598000168800354},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7178999781608582},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6492999792098999},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6403999924659729},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.49149999022483826},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.45910000801086426},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.44749999046325684},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.38769999146461487},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.3723999857902527}],"concepts":[{"id":"https://openalex.org/C2779110517","wikidata":"https://www.wikidata.org/wiki/Q1240788","display_name":"Supervisor","level":2,"score":0.7598000168800354},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7407000064849854},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7178999781608582},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6492999792098999},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6403999924659729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6225000023841858},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5404000282287598},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.49149999022483826},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.45910000801086426},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.44749999046325684},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.38769999146461487},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.3723999857902527},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.37070000171661377},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3653999865055084},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.35510000586509705},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3093999922275543},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30790001153945923},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3037000000476837},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.265500009059906}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/make7040126","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make7040126","pdf_url":"https://www.mdpi.com/2504-4990/7/4/126/pdf?version=1761140806","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:b2d9dc43ae744c119b2ccdf8866c057d","is_oa":true,"landing_page_url":"https://doaj.org/article/b2d9dc43ae744c119b2ccdf8866c057d","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Machine Learning and Knowledge Extraction, Vol 7, Iss 4, p 126 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/make7040126","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make7040126","pdf_url":"https://www.mdpi.com/2504-4990/7/4/126/pdf?version=1761140806","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415452640.pdf"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W2151834591","https://openalex.org/W2296073425","https://openalex.org/W2923622379","https://openalex.org/W2963523627","https://openalex.org/W2972758308","https://openalex.org/W3027406032","https://openalex.org/W3160638507","https://openalex.org/W3174394955","https://openalex.org/W4300630456","https://openalex.org/W4393763811","https://openalex.org/W4400281131","https://openalex.org/W4401392383","https://openalex.org/W4405145750"],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,175],"(RL)":[2],"agents":[3],"face":[4],"significant":[5],"challenges":[6],"in":[7,19,180,184],"sparse-reward":[8,195],"environments,":[9],"as":[10],"insufficient":[11],"exploration":[12,179],"of":[13,43,57,134,154],"the":[14,40,77,89,112,118,132,150],"state":[15],"space":[16],"can":[17,69,114],"result":[18],"inefficient":[20],"training":[21,186],"or":[22],"incomplete":[23],"policy":[24,119],"learning.":[25],"To":[26],"address":[27],"this":[28,30,85,128],"challenge,":[29],"work":[31],"proposes":[32],"a":[33,79],"teacher\u2013student":[34,147,170,191],"framework":[35,148,171],"for":[36,194],"RL":[37],"that":[38,111,158,168],"leverages":[39],"inherent":[41],"knowledge":[42],"large":[44],"language":[45],"models":[46],"(LLMs)":[47],"to":[48,59,72,76,105,161],"decompose":[49],"complex":[50,181],"tasks":[51],"into":[52],"manageable":[53],"subgoals.":[54],"The":[55],"capabilities":[56],"LLMs":[58,137],"comprehend":[60],"problem":[61],"structure":[62],"and":[63,96,109,141,176,188],"objectives,":[64],"based":[65],"on":[66,149],"textual":[67],"descriptions,":[68],"be":[70,115],"harnessed":[71],"generate":[73],"subgoals,":[74],"similar":[75],"guidance":[78],"human":[80],"supervisor":[81,113],"would":[82],"provide.":[83],"For":[84],"purpose,":[86],"we":[87,99,130,144],"introduce":[88],"following":[90],"three":[91,135],"subgoal":[92],"types:":[93],"positional,":[94],"representation-based,":[95],"language-based.":[97],"Moreover,":[98],"propose":[100],"an":[101],"LLM":[102],"surrogate":[103],"model":[104],"reduce":[106],"computational":[107,125],"overhead":[108],"demonstrate":[110],"decoupled":[116],"once":[117],"has":[120],"been":[121],"learned,":[122],"further":[123],"lowering":[124],"costs.":[126],"Under":[127],"framework,":[129],"evaluate":[131],"performance":[133],"open-source":[136],"(namely,":[138],"Llama,":[139],"DeepSeek,":[140],"Qwen).":[142],"Furthermore,":[143],"assess":[145],"our":[146,169],"MiniGrid":[151],"benchmark\u2014a":[152],"collection":[153],"procedurally":[155],"generated":[156],"environments":[157],"demand":[159],"generalization":[160],"previously":[162],"unseen":[163],"tasks.":[164],"Experimental":[165],"results":[166],"indicate":[167],"facilitates":[172],"more":[173],"efficient":[174],"encourages":[177],"enhanced":[178],"tasks,":[182],"resulting":[183],"faster":[185],"convergence":[187],"outperforming":[189],"recent":[190],"methods":[192],"designed":[193],"environments.":[196]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-24T00:00:00"}