{"id":"https://openalex.org/W4410287760","doi":"https://doi.org/10.1007/s00778-025-00920-0","title":"Model reusability in Reinforcement Learning","display_name":"Model reusability in Reinforcement Learning","publication_year":2025,"publication_date":"2025-05-12","ids":{"openalex":"https://openalex.org/W4410287760","doi":"https://doi.org/10.1007/s00778-025-00920-0"},"language":"en","primary_location":{"id":"doi:10.1007/s00778-025-00920-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00778-025-00920-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00778-025-00920-0.pdf","source":{"id":"https://openalex.org/S78926909","display_name":"The VLDB Journal","issn_l":"0949-877X","issn":["0949-877X","1066-8888"],"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":"The VLDB Journal","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/s00778-025-00920-0.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069238664","display_name":"Sepideh Nikookar","orcid":"https://orcid.org/0000-0003-0181-3567"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]},{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sepideh Nikookar","raw_affiliation_strings":["Emory University, Atlanta, USA","New Jersey Institute of Technology, Newark, USA"],"affiliations":[{"raw_affiliation_string":"Emory University, Atlanta, USA","institution_ids":["https://openalex.org/I150468666"]},{"raw_affiliation_string":"New Jersey Institute of Technology, Newark, USA","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116335869","display_name":"Sohrab Namazi Nia","orcid":"https://orcid.org/0009-0008-5167-9881"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sohrab Namazi Nia","raw_affiliation_strings":["New Jersey Institute of Technology, Newark, USA"],"affiliations":[{"raw_affiliation_string":"New Jersey Institute of Technology, Newark, USA","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009377962","display_name":"Senjuti Basu Roy","orcid":"https://orcid.org/0000-0003-3475-8138"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Senjuti Basu Roy","raw_affiliation_strings":["New Jersey Institute of Technology, Newark, USA"],"affiliations":[{"raw_affiliation_string":"New Jersey Institute of Technology, Newark, USA","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081664259","display_name":"Sihem Amer-Yahia","orcid":"https://orcid.org/0000-0002-6194-4502"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Sihem Amer-Yahia","raw_affiliation_strings":["CNRS, University Grenoble Alpes, Grenoble, France"],"affiliations":[{"raw_affiliation_string":"CNRS, University Grenoble Alpes, Grenoble, France","institution_ids":["https://openalex.org/I899635006","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074877973","display_name":"Behrooz Omidvar-Tehrani","orcid":"https://orcid.org/0000-0001-9103-0114"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Behrooz Omidvar-Tehrani","raw_affiliation_strings":["Amazon AWS AI, Ohio, USA"],"affiliations":[{"raw_affiliation_string":"Amazon AWS AI, Ohio, USA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5069238664"],"corresponding_institution_ids":["https://openalex.org/I118118575","https://openalex.org/I150468666"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":{"value":2290,"currency":"EUR","value_usd":2890},"fwci":18.7452,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.99052363,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"34","issue":"4","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":0.9984999895095825,"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":0.9984999895095825,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9940000176429749,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9934999942779541,"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/reusability","display_name":"Reusability","score":0.8572921752929688},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7222131490707397},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5172055959701538},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4999697208404541},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22207310795783997},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1651979386806488},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13741305470466614},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.05505335330963135},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.04634511470794678}],"concepts":[{"id":"https://openalex.org/C137981799","wikidata":"https://www.wikidata.org/wiki/Q1369184","display_name":"Reusability","level":3,"score":0.8572921752929688},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7222131490707397},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5172055959701538},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4999697208404541},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22207310795783997},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1651979386806488},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13741305470466614},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.05505335330963135},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.04634511470794678}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s00778-025-00920-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00778-025-00920-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00778-025-00920-0.pdf","source":{"id":"https://openalex.org/S78926909","display_name":"The VLDB Journal","issn_l":"0949-877X","issn":["0949-877X","1066-8888"],"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":"The VLDB Journal","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-05335723v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-05335723","pdf_url":null,"source":{"id":"https://openalex.org/S4406922466","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"The VLDB Journal, 2025, 34 (4), pp.41. ⟨10.1007/s00778-025-00920-0⟩","raw_type":"Journal articles"}],"best_oa_location":{"id":"doi:10.1007/s00778-025-00920-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00778-025-00920-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00778-025-00920-0.pdf","source":{"id":"https://openalex.org/S78926909","display_name":"The VLDB Journal","issn_l":"0949-877X","issn":["0949-877X","1066-8888"],"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":"The VLDB Journal","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1714017558","display_name":"Superbursts: Multi-dimensional Simulations of Deep Carbon Explosions on Neutron Stars","funder_award_id":"1812838","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G223175938","display_name":null,"funder_award_id":"N000141812838","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G3761471208","display_name":"Collaborative Research:  Biomass Burning Emissions Over Southern Africa","funder_award_id":"0001424","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3838391714","display_name":null,"funder_award_id":"997694","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G4176610780","display_name":null,"funder_award_id":"997356","funder_id":"https://openalex.org/F4320337389","funder_display_name":"Division of Information and Intelligent Systems"},{"id":"https://openalex.org/G5921281487","display_name":null,"funder_award_id":"number","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6406752454","display_name":"III: Small: Collaborative Research: An Optimization Framework for Designing Derived Attributes with Humans-in-the-loop","funder_award_id":"2007935","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6452577645","display_name":"Collaborative Research: Creating mechanisms to make integrative structures of large macromolecular assemblies available from the Protein Data Bank","funder_award_id":"2112966","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7662934342","display_name":null,"funder_award_id":"997041","funder_id":"https://openalex.org/F4320338298","funder_display_name":"Office of Naval Research Global"},{"id":"https://openalex.org/G8187264017","display_name":null,"funder_award_id":"1814595","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8192954037","display_name":"CAREER:  Streamlining Task Deployment on Crowdsourcing Platforms","funder_award_id":"1942913","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8521011827","display_name":null,"funder_award_id":"997427","funder_id":"https://openalex.org/F4320337389","funder_display_name":"Division of Information and Intelligent Systems"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320337389","display_name":"Division of Information and Intelligent Systems","ror":"https://ror.org/053a2cp42"},{"id":"https://openalex.org/F4320338298","display_name":"Office of Naval Research Global","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410287760.pdf","grobid_xml":"https://content.openalex.org/works/W4410287760.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1506126330","https://openalex.org/W1981276685","https://openalex.org/W2012036715","https://openalex.org/W2058702778","https://openalex.org/W2072758956","https://openalex.org/W2082806890","https://openalex.org/W2107726111","https://openalex.org/W2113913482","https://openalex.org/W2128362607","https://openalex.org/W2132862423","https://openalex.org/W2151161180","https://openalex.org/W2169209873","https://openalex.org/W2541884796","https://openalex.org/W2546571074","https://openalex.org/W2562337727","https://openalex.org/W2789543555","https://openalex.org/W2809148419","https://openalex.org/W2877093712","https://openalex.org/W2946504770","https://openalex.org/W2962771342","https://openalex.org/W2964209691","https://openalex.org/W2964227312","https://openalex.org/W2979826702","https://openalex.org/W3031617143","https://openalex.org/W3037665057","https://openalex.org/W3081310128","https://openalex.org/W3100789280","https://openalex.org/W3157980612","https://openalex.org/W4214717370","https://openalex.org/W4233817995","https://openalex.org/W4255421341","https://openalex.org/W4281890931","https://openalex.org/W4281976908","https://openalex.org/W4285338532","https://openalex.org/W4288057685","https://openalex.org/W4289533818","https://openalex.org/W4306317685","https://openalex.org/W4323073011","https://openalex.org/W6600175266","https://openalex.org/W6702248584"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4282938614","https://openalex.org/W2906929912","https://openalex.org/W2350686889","https://openalex.org/W1965839502","https://openalex.org/W2099755394","https://openalex.org/W2621742671","https://openalex.org/W2114764029"],"abstract_inverted_index":{"Abstract":[0],"The":[1,93],"ability":[2],"to":[3,32,81],"reuse":[4],"trained":[5,52,109],"models":[6,28],"in":[7,15,29],"Reinforcement":[8],"Learning":[9,71],"(RL)":[10],"holds":[11],"substantial":[12],"practical":[13],"value":[14],"particular":[16],"for":[17,26,48],"complex":[18],"tasks.":[19],"While":[20],"model":[21,66],"reusability":[22],"is":[23,39,46,79],"widely":[24],"studied":[25],"supervised":[27],"data":[30,65],"management,":[31],"the":[33,40,104,145],"best":[34],"of":[35,149],"our":[36,141,150],"knowledge,":[37],"this":[38],"first":[41],"ever":[42],"principled":[43],"study":[44],"that":[45,67,86,101,117],"proposed":[47],"RL.":[49],"To":[50],"capture":[51,82],"policies,":[53],"we":[54],"develop":[55],"a":[56,114,119],"framework":[57,78,94],"based":[58,74],"on":[59],"an":[60],"expressive":[61],"and":[62,72,99,123,137,143,147],"lossless":[63],"graph":[64],"accommodates":[68],"Temporal":[69],"Difference":[70],"Deep-RL":[73],"RL":[75,133],"algorithms.":[76,151],"Our":[77,128],"able":[80],"arbitrary":[83],"reward":[84],"functions":[85],"can":[87],"be":[88],"composed":[89],"at":[90],"inference":[91],"time.":[92],"comes":[95],"with":[96,130],"theoretical":[97],"guarantees":[98],"shows":[100],"it":[102],"yields":[103],"same":[105],"result":[106],"as":[107],"policies":[108],"from":[110],"scratch.":[111],"We":[112],"design":[113],"parameterized":[115],"algorithm":[116],"strikes":[118],"balance":[120],"between":[121],"efficiency":[122,148],"quality":[124],"w.r.t":[125],"cumulative":[126],"reward.":[127],"experiments":[129],"two":[131],"common":[132],"tasks":[134],"(query":[135],"refinement":[136],"robot":[138],"movement)":[139],"corroborate":[140],"theory":[142],"show":[144],"effectiveness":[146]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}