{"id":"https://openalex.org/W4409163693","doi":"https://doi.org/10.1007/s00521-025-11156-y","title":"LaGR-SEQ: Language-guided reinforcement learning with sample-efficient querying","display_name":"LaGR-SEQ: Language-guided reinforcement learning with sample-efficient querying","publication_year":2025,"publication_date":"2025-04-02","ids":{"openalex":"https://openalex.org/W4409163693","doi":"https://doi.org/10.1007/s00521-025-11156-y"},"language":"en","primary_location":{"id":"doi:10.1007/s00521-025-11156-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-025-11156-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-025-11156-y.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s00521-025-11156-y.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043916805","display_name":"Thommen George Karimpanal","orcid":"https://orcid.org/0000-0001-8918-3314"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Thommen Karimpanal George","raw_affiliation_strings":["School of Information Technology, Deakin University, 75 Pigdons Road, Waurn Ponds, VIC, 3216, Australia"],"raw_orcid":"https://orcid.org/0000-0001-8918-3314","affiliations":[{"raw_affiliation_string":"School of Information Technology, Deakin University, 75 Pigdons Road, Waurn Ponds, VIC, 3216, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019310532","display_name":"Buddhika Laknath Semage","orcid":"https://orcid.org/0000-0002-2792-492X"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Buddhika Laknath Semage","raw_affiliation_strings":["Applied Artificial Intelligence Institute, Deakin University, 75 Pigdons Road, Waurn Ponds, VIC, 3216, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Applied Artificial Intelligence Institute, Deakin University, 75 Pigdons Road, Waurn Ponds, VIC, 3216, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024215125","display_name":"Santu Rana","orcid":"https://orcid.org/0000-0003-2247-850X"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Santu Rana","raw_affiliation_strings":["Applied Artificial Intelligence Institute, Deakin University, 75 Pigdons Road, Waurn Ponds, VIC, 3216, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Applied Artificial Intelligence Institute, Deakin University, 75 Pigdons Road, Waurn Ponds, VIC, 3216, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101936199","display_name":"Hung L\u00ea","orcid":"https://orcid.org/0000-0002-3126-184X"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hung Le","raw_affiliation_strings":["Applied Artificial Intelligence Institute, Deakin University, 75 Pigdons Road, Waurn Ponds, VIC, 3216, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Applied Artificial Intelligence Institute, Deakin University, 75 Pigdons Road, Waurn Ponds, VIC, 3216, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085471517","display_name":"Truyen Tran","orcid":"https://orcid.org/0000-0001-6531-8907"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Truyen Tran","raw_affiliation_strings":["Applied Artificial Intelligence Institute, Deakin University, 75 Pigdons Road, Waurn Ponds, VIC, 3216, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Applied Artificial Intelligence Institute, Deakin University, 75 Pigdons Road, Waurn Ponds, VIC, 3216, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011012522","display_name":"Sunil Gupta","orcid":"https://orcid.org/0000-0002-4669-9940"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sunil Gupta","raw_affiliation_strings":["Applied Artificial Intelligence Institute, Deakin University, 75 Pigdons Road, Waurn Ponds, VIC, 3216, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Applied Artificial Intelligence Institute, Deakin University, 75 Pigdons Road, Waurn Ponds, VIC, 3216, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045540854","display_name":"Svetha Venkatesh","orcid":"https://orcid.org/0000-0001-8675-6631"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Svetha Venkatesh","raw_affiliation_strings":["Applied Artificial Intelligence Institute, Deakin University, 75 Pigdons Road, Waurn Ponds, VIC, 3216, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Applied Artificial Intelligence Institute, Deakin University, 75 Pigdons Road, Waurn Ponds, VIC, 3216, Australia","institution_ids":["https://openalex.org/I149704539"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5043916805"],"corresponding_institution_ids":["https://openalex.org/I149704539"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02856225,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"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":0.9998000264167786,"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":0.9998000264167786,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computational-science-and-engineering","display_name":"Computational Science and Engineering","score":0.905232310295105},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8319940567016602},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7686904668807983},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.7422794699668884},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5417535901069641},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5402500629425049},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44431939721107483},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3418455123901367},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08419987559318542}],"concepts":[{"id":"https://openalex.org/C68597687","wikidata":"https://www.wikidata.org/wiki/Q362601","display_name":"Computational Science and Engineering","level":2,"score":0.905232310295105},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8319940567016602},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7686904668807983},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.7422794699668884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5417535901069641},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5402500629425049},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44431939721107483},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3418455123901367},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08419987559318542},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s00521-025-11156-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-025-11156-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-025-11156-y.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},{"id":"pmh:oai:figshare.com:article/28793897","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/LaGR-SEQ_Language-guided_reinforcement_learning_with_sample-efficient_querying/28793897","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1007/s00521-025-11156-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-025-11156-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-025-11156-y.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320970","display_name":"Deakin University","ror":"https://ror.org/02czsnj07"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409163693.pdf","grobid_xml":"https://content.openalex.org/works/W4409163693.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1977655452","https://openalex.org/W1981276685","https://openalex.org/W2145339207","https://openalex.org/W2901461022","https://openalex.org/W2963800628","https://openalex.org/W3034758614","https://openalex.org/W3101378920","https://openalex.org/W3152878473","https://openalex.org/W3176484337","https://openalex.org/W4206275166","https://openalex.org/W4221055872","https://openalex.org/W4312594400","https://openalex.org/W4323655724","https://openalex.org/W4384200891","https://openalex.org/W6600263792","https://openalex.org/W6600710808","https://openalex.org/W6603707631","https://openalex.org/W6603932791","https://openalex.org/W6610527797","https://openalex.org/W6610659411","https://openalex.org/W6628007242"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"Abstract":[0],"Large":[1],"language":[2],"models":[3],"(LLMs)":[4],"have":[5,99],"recently":[6],"demonstrated":[7],"their":[8],"impressive":[9],"ability":[10,18,90],"to":[11,23,33,93,96,112,167,192,216],"provide":[12],"context-aware":[13],"responses":[14],"via":[15],"text.":[16],"This":[17],"could":[19],"potentially":[20],"be":[21,57,135,144,173],"used":[22],"predict":[24,47],"plausible":[25],"solutions":[26,95,184],"in":[27,51,71,110],"sequential":[28],"decision":[29],"making":[30],"tasks":[31,97,227],"pertaining":[32],"pattern":[34],"completion.":[35],"For":[36],"example,":[37],"by":[38,59,103],"observing":[39],"a":[40,104,140,163,224],"partial":[41,73],"stack":[42],"of":[43,91,182,214,226,232],"cubes,":[44],"LLMs":[45,92],"can":[46,143],"the":[48,53,61,72,115,133,170,180,183,187,190,212,217,230],"correct":[49],"sequence":[50],"which":[52,86],"remaining":[54],"cubes":[55],"should":[56,172],"stacked":[58],"extrapolating":[60],"observed":[62],"patterns":[63],"(e.g.,":[64],"cube":[65],"sizes,":[66],"colors":[67],"or":[68],"other":[69],"attributes)":[70],"stack.":[74],"In":[75],"this":[76,88,127,150,194],"work,":[77],"we":[78,152,160,178],"introduce":[79,153],"LaGR":[80],"(":[81,155],"language-guided":[82],"reinforcement":[83,106],"learning":[84,107],"),":[85,158],"uses":[87],"predictive":[89],"propose":[94],"that":[98,132,142,198],"been":[100],"partially":[101],"completed":[102],"primary":[105,206],"(RL)":[108],"agent,":[109],"order":[111],"subsequently":[113],"guide":[114],"latter\u2019s":[116],"training.":[117],"However,":[118],"as":[119,189],"RL":[120,165,207],"training":[121],"is":[122],"generally":[123],"not":[124],"sample-efficient,":[125],"deploying":[126],"approach":[128,222],"would":[129],"inherently":[130],"imply":[131],"LLM":[134,171,188],"repeatedly":[136],"queried":[137,174],"for":[138,175],"solutions;":[139],"process":[141],"expensive":[145],"and":[146,228,239],"infeasible.":[147],"To":[148],"address":[149],"issue,":[151],"SEQ":[154],"sample-efficient":[156],"querying":[157],"where":[159],"simultaneously":[161,210],"train":[162,193],"secondary":[164],"agent":[166],"decide":[168],"when":[169],"solutions.":[176],"Specifically,":[177],"use":[179],"quality":[181],"emanating":[185],"from":[186],"reward":[191],"agent.":[195],"We":[196,219],"show":[197],"our":[199,221,233],"proposed":[200],"framework":[201],"LaGR-SEQ":[202],"enables":[203],"more":[204],"efficient":[205],"training,":[208],"while":[209],"minimizing":[211],"number":[213],"queries":[215],"LLM.":[218],"demonstrate":[220],"on":[223],"series":[225],"highlight":[229],"advantages":[231],"approach,":[234],"along":[235],"with":[236],"its":[237],"limitations":[238],"potential":[240],"future":[241],"research":[242],"directions.":[243]},"counts_by_year":[],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}