{"id":"https://openalex.org/W4413925071","doi":"https://doi.org/10.1109/icra55743.2025.11127622","title":"ExploRLLM: Guiding Exploration in Reinforcement Learning with Large Language Models","display_name":"ExploRLLM: Guiding Exploration in Reinforcement Learning with Large Language Models","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413925071","doi":"https://doi.org/10.1109/icra55743.2025.11127622"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11127622","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127622","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":"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/A5110990989","display_name":"Runyu Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Runyu Ma","raw_affiliation_strings":["Cognitive Robotics, Delft University of Technology,The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cognitive Robotics, Delft University of Technology,The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027731507","display_name":"Jelle Luijkx","orcid":"https://orcid.org/0009-0002-7099-3741"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Jelle Luijkx","raw_affiliation_strings":["Cognitive Robotics, Delft University of Technology,The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cognitive Robotics, Delft University of Technology,The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051560432","display_name":"Zlatan Ajanovi\u0107","orcid":"https://orcid.org/0000-0003-2214-0007"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Zlatan Ajanovi\u0107","raw_affiliation_strings":["RWTH Aachen University,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035229829","display_name":"Jens Kober","orcid":"https://orcid.org/0000-0001-7257-5434"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Jens Kober","raw_affiliation_strings":["Cognitive Robotics, Delft University of Technology,The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cognitive Robotics, Delft University of Technology,The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9011","last_page":"9017"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.850600004196167,"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":0.850600004196167,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.7940999865531921,"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":0.7829601764678955},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6884216070175171},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.39062023162841797},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.365823894739151},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.3208036422729492},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1359097957611084}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7829601764678955},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6884216070175171},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39062023162841797},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.365823894739151},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3208036422729492},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1359097957611084}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11127622","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127622","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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1977655452","https://openalex.org/W2951360122","https://openalex.org/W4383097638","https://openalex.org/W4383108457","https://openalex.org/W4396877948","https://openalex.org/W4401417060","https://openalex.org/W4401417348"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2138720691","https://openalex.org/W2376932109"],"abstract_inverted_index":{"In":[0,59],"robot":[1],"manipulation,":[2],"Reinforcement":[3],"Learning":[4],"(RL)":[5],"often":[6],"suffers":[7],"from":[8,93],"low":[9],"sample":[10],"efficiency":[11],"and":[12,19,32,44,70,95],"uncertain":[13],"convergence,":[14],"especially":[15],"in":[16,30,98],"large":[17],"observation":[18],"action":[20],"spaces.":[21],"Foundation":[22],"Models":[23],"(FMs)":[24],"offer":[25],"an":[26],"alternative,":[27],"demonstrating":[28],"promise":[29],"zero-shot":[31,111],"few-shot":[33],"settings.":[34],"However,":[35],"they":[36],"can":[37],"be":[38],"unreliable":[39],"due":[40],"to":[41],"limited":[42,82],"physical":[43,83],"spatial":[45],"understanding.":[46,84],"We":[47,85],"introduce":[48],"ExploRLLM,":[49],"a":[50,74],"method":[51],"that":[52,87,106],"combines":[53],"the":[54,80,107],"strengths":[55],"of":[56],"both":[57,90],"paradigms.":[58],"our":[60],"approach,":[61],"FMs":[62,94],"improve":[63],"RL":[64,76,96],"convergence":[65],"by":[66],"generating":[67],"policy":[68],"code":[69],"efficient":[71],"representations,":[72],"while":[73],"residual":[75],"agent":[77],"compensates":[78],"for":[79],"FMs'":[81],"show":[86,105],"Explorllm":[88],"outperforms":[89],"policies":[91,108],"derived":[92],"baselines":[97],"table-top":[99],"manipulation":[100],"tasks.":[101],"Additionally,":[102],"real-world":[103],"experiments":[104],"exhibit":[109],"promising":[110],"sim-to-real":[112],"transfer.":[113],"Supplementary":[114],"material":[115],"is":[116],"available":[117],"at":[118],"https://explorllm.github.io.":[119]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}