{"id":"https://openalex.org/W4319453286","doi":"https://doi.org/10.48550/arxiv.2302.02662","title":"Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning","display_name":"Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning","publication_year":2023,"publication_date":"2023-02-06","ids":{"openalex":"https://openalex.org/W4319453286","doi":"https://doi.org/10.48550/arxiv.2302.02662"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2302.02662","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2302.02662","pdf_url":"https://arxiv.org/pdf/2302.02662","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2302.02662","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039026472","display_name":"Thomas Carta","orcid":"https://orcid.org/0000-0003-3145-549X","observed_orcids":["https://orcid.org/0000-0003-3145-549X"]},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I15057530","display_name":"Universit\u00e9 de Bordeaux","ror":"https://ror.org/057qpr032","country_code":"FR","type":"education","lineage":["https://openalex.org/I15057530"]},{"id":"https://openalex.org/I49451733","display_name":"Universit\u00e9 d'Angers","ror":"https://ror.org/04yrqp957","country_code":"FR","type":"education","lineage":["https://openalex.org/I49451733"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Carta, Thomas","raw_affiliation_strings":["Inria (Flowers ) University of Bordeaux , France","Sylvain Lamprier Univ Angers , LERIA , SFR MATHSTIC , F-49000 Angers , France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria (Flowers ) University of Bordeaux , France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I15057530"]},{"raw_affiliation_string":"Sylvain Lamprier Univ Angers , LERIA , SFR MATHSTIC , F-49000 Angers , France","institution_ids":["https://openalex.org/I49451733"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072955860","display_name":"Cl\u00e9ment Romac","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I15057530","display_name":"Universit\u00e9 de Bordeaux","ror":"https://ror.org/057qpr032","country_code":"FR","type":"education","lineage":["https://openalex.org/I15057530"]},{"id":"https://openalex.org/I4387154989","display_name":"Hugging Face","ror":"https://ror.org/02grspc61","country_code":"US","type":"company","lineage":["https://openalex.org/I4387154989"]}],"countries":["FR","US"],"is_corresponding":false,"raw_author_name":"Romac, Cl\u00e9ment","raw_affiliation_strings":["Hugging","Inria (Flowers ) University of Bordeaux , France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hugging","institution_ids":["https://openalex.org/I4387154989"]},{"raw_affiliation_string":"Inria (Flowers ) University of Bordeaux , France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I15057530"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055402965","display_name":"Thomas Wolf","orcid":"https://orcid.org/0000-0002-9781-3459","observed_orcids":["https://orcid.org/0000-0002-9781-3459"]},"institutions":[{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210150358","display_name":"Institut Syst\u00e8mes Intelligents et de Robotique","ror":"https://ror.org/05neq8668","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I154526488","https://openalex.org/I39804081","https://openalex.org/I4210150358","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Wolf, Thomas","raw_affiliation_strings":["Sorbonne Universit\u00e9 , ISIR , Paris , France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sorbonne Universit\u00e9 , ISIR , Paris , France","institution_ids":["https://openalex.org/I39804081","https://openalex.org/I4210150358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031635996","display_name":"Sylvain Lamprier","orcid":"https://orcid.org/0000-0002-2508-922X","observed_orcids":["https://orcid.org/0000-0002-2508-922X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lamprier, Sylvain","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042850624","display_name":"Olivier Sigaud","orcid":"https://orcid.org/0000-0002-8544-0229","observed_orcids":["https://orcid.org/0000-0002-8544-0229"]},"institutions":[{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210150358","display_name":"Institut Syst\u00e8mes Intelligents et de Robotique","ror":"https://ror.org/05neq8668","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I154526488","https://openalex.org/I39804081","https://openalex.org/I4210150358","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Sigaud, Olivier","raw_affiliation_strings":["Sorbonne Universit\u00e9 , ISIR , Paris , France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sorbonne Universit\u00e9 , ISIR , Paris , France","institution_ids":["https://openalex.org/I39804081","https://openalex.org/I4210150358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112309835","display_name":"Pierre\u2010Yves Oudeyer","orcid":"https://orcid.org/0000-0002-1277-130X","observed_orcids":["https://orcid.org/0000-0002-1277-130X"]},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I15057530","display_name":"Universit\u00e9 de Bordeaux","ror":"https://ror.org/057qpr032","country_code":"FR","type":"education","lineage":["https://openalex.org/I15057530"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Oudeyer, Pierre-Yves","raw_affiliation_strings":["Inria (Flowers ) University of Bordeaux , France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria (Flowers ) University of Bordeaux , France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I15057530"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":114,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"202","issue":"3676-3713","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9955999851226807,"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":0.9955999851226807,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.0012000000569969416,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0005000000237487257,"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/large-language-models","display_name":"large language models","score":0.8809999823570251},{"id":"https://openalex.org/keywords/online-reinforcement-learning","display_name":"online reinforcement learning","score":0.9660000205039978},{"id":"https://openalex.org/keywords/sample-efficiency","display_name":"sample efficiency","score":0.7829999923706055},{"id":"https://openalex.org/keywords/generalization","display_name":"generalization","score":0.9150000214576721},{"id":"https://openalex.org/keywords/navigation-tasks","display_name":"navigation tasks","score":0.7620000243186951},{"id":"https://openalex.org/keywords/spatial-reasoning","display_name":"spatial reasoning","score":0.7609999775886536},{"id":"https://openalex.org/keywords/flan-t5","display_name":"Flan-T5","score":0.9269999861717224}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7095687389373779},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6983909010887146},{"id":"https://openalex.org/C100521375","wikidata":"https://www.wikidata.org/wiki/Q2015382","display_name":"Competence (human resources)","level":2,"score":0.6740486025810242},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6177490949630737},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.552578866481781},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4693875014781952},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.42809516191482544},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4044061601161957},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12421223521232605},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07743492722511292},{"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:arXiv.org:2302.02662","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2302.02662","pdf_url":"https://arxiv.org/pdf/2302.02662","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:HAL:hal-03970122v3","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-03970122v3","pdf_url":"https://hal.science/hal-03970122v3/file/extended_version.pdf","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Machine Learning 2023, Jul 2023, Honololu, Hawaii, United States","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:HAL:hal-03970122v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-03970122v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://hal.science/hal-03970122","raw_type":"info:eu-repo/semantics/preprint"},{"id":"doi:10.48550/arxiv.2302.02662","doi":"https://doi.org/10.48550/arxiv.2302.02662","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2302.02662","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2302.02662","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2302.02662","pdf_url":"https://arxiv.org/pdf/2302.02662","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G4389353301","display_name":"Purposeful Intrinsically motivated Lifelong Learning Autonomous Robots","funder_award_id":"101070381","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8315783592","display_name":null,"funder_award_id":"101070381","funder_id":"https://openalex.org/F4320334322","funder_display_name":"HORIZON EUROPE Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320326256","display_name":"Grand \u00c9quipement National De Calcul Intensif","ror":"https://ror.org/0010d1q40"},{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4319453286.pdf","grobid_xml":"https://content.openalex.org/works/W4319453286.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W1986227429","https://openalex.org/W2562682442","https://openalex.org/W2808979760","https://openalex.org/W2920277907","https://openalex.org/W2962690183","https://openalex.org/W3020712669","https://openalex.org/W3027086341","https://openalex.org/W3034723486","https://openalex.org/W3135367836","https://openalex.org/W3177898556"],"related_works":["https://openalex.org/W4391272737","https://openalex.org/W4414360787","https://openalex.org/W4399240167","https://openalex.org/W4404338615","https://openalex.org/W7131044385","https://openalex.org/W4386501856","https://openalex.org/W7165758137","https://openalex.org/W4411179911","https://openalex.org/W4394867908","https://openalex.org/W4413141447"],"abstract_inverted_index":{"Recent":[0],"works":[1],"successfully":[2],"leveraged":[3],"Large":[4],"Language":[5],"Models'":[6],"(LLM)":[7],"abilities":[8],"to":[9,16,37,50,82,86,95],"capture":[10],"abstract":[11],"knowledge":[12,25],"about":[13],"world's":[14],"physics":[15],"solve":[17,87],"decision-making":[18],"problems.":[19],"Yet,":[20],"the":[21,27,72,76,140],"alignment":[22,53],"between":[23],"LLMs'":[24],"and":[26,32,102,107],"environment":[28,93],"can":[29,130],"be":[30],"wrong":[31],"limit":[33],"functional":[34,55,100],"competence":[35],"due":[36],"lack":[38],"of":[39,99,105,124,135,142,156],"grounding.":[40],"In":[41],"this":[42,52],"paper,":[43],"we":[44,57,110],"study":[45,96,111,146],"an":[46,59,62,90],"approach":[47],"(named":[48],"GLAM)":[49],"achieve":[51],"through":[54],"grounding:":[56],"consider":[58],"agent":[60,73],"using":[61],"LLM":[63],"as":[64,71],"a":[65,103],"policy":[66],"that":[67],"is":[68,139],"progressively":[69],"updated":[70],"interacts":[74],"with":[75],"environment,":[77],"leveraging":[78],"online":[79,122,143],"Reinforcement":[80],"Learning":[81],"improve":[83],"its":[84],"performance":[85],"goals.":[88],"Using":[89],"interactive":[91],"textual":[92],"designed":[94],"higher-level":[97],"forms":[98,134],"grounding,":[101],"set":[104],"spatial":[106],"navigation":[108],"tasks,":[109],"several":[112,152],"scientific":[113],"questions:":[114],"1)":[115],"Can":[116],"LLMs":[117],"boost":[118,132],"sample":[119],"efficiency":[120],"for":[121],"learning":[123],"various":[125],"RL":[126],"tasks?":[127],"2)":[128],"How":[129],"it":[131],"different":[133],"generalization?":[136],"3)":[137],"What":[138],"impact":[141],"learning?":[144],"We":[145],"these":[147],"questions":[148],"by":[149],"functionally":[150],"grounding":[151],"variants":[153],"(size,":[154],"architecture)":[155],"FLAN-T5.":[157]},"counts_by_year":[{"year":2026,"cited_by_count":13},{"year":2025,"cited_by_count":29},{"year":2024,"cited_by_count":38},{"year":2023,"cited_by_count":34}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2023-02-09T00:00:00"}