{"id":"https://openalex.org/W7134915135","doi":"https://doi.org/10.1007/s10458-026-09739-7","title":"Quantification of transfer in reinforcement learning via regret bounds for learning agents","display_name":"Quantification of transfer in reinforcement learning via regret bounds for learning agents","publication_year":2026,"publication_date":"2026-03-11","ids":{"openalex":"https://openalex.org/W7134915135","doi":"https://doi.org/10.1007/s10458-026-09739-7"},"language":"en","primary_location":{"id":"doi:10.1007/s10458-026-09739-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10458-026-09739-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10458-026-09739-7.pdf","source":{"id":"https://openalex.org/S5405189","display_name":"Autonomous Agents and Multi-Agent Systems","issn_l":"1387-2532","issn":["1387-2532","1573-7454"],"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":"Autonomous Agents and Multi-Agent Systems","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/s10458-026-09739-7.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128759689","display_name":"Adrienne Tuynman","orcid":null},"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/I2279609970","display_name":"Universit\u00e9 de Lille","ror":"https://ror.org/02kzqn938","country_code":"FR","type":"education","lineage":["https://openalex.org/I2279609970"]},{"id":"https://openalex.org/I7454413","display_name":"\u00c9cole Centrale de Lille","ror":"https://ror.org/01x441g73","country_code":"FR","type":"education","lineage":["https://openalex.org/I7454413"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Adrienne Tuynman","raw_affiliation_strings":["Scool team, Univ. Lille, Inria, CNRS, Centrale Lille, UMR 9189 CRIStAL, Lille, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Scool team, Univ. Lille, Inria, CNRS, Centrale Lille, UMR 9189 CRIStAL, Lille, France","institution_ids":["https://openalex.org/I2279609970","https://openalex.org/I7454413","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5095183845","display_name":"Ronald Ortner","orcid":null},"institutions":[{"id":"https://openalex.org/I182712176","display_name":"Montanuniversit\u00e4t Leoben","ror":"https://ror.org/02fhfw393","country_code":"AT","type":"education","lineage":["https://openalex.org/I182712176"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Ronald Ortner","raw_affiliation_strings":["Lehrstuhl f\u00fcr Informationstechnologie, Montanuniversit\u00e4t Leoben, Leoben, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lehrstuhl f\u00fcr Informationstechnologie, Montanuniversit\u00e4t Leoben, Leoben, Austria","institution_ids":["https://openalex.org/I182712176"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5095183845"],"corresponding_institution_ids":["https://openalex.org/I182712176"],"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":0.42401207,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.48510000109672546,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.48510000109672546,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.4171999990940094,"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/T11031","display_name":"Game Theory and Applications","score":0.024800000712275505,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5855000019073486},{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.4507000148296356},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4133000075817108},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.35359999537467957},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3160000145435333}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5855000019073486},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5472999811172485},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5286999940872192},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.4507000148296356},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4133000075817108},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.35359999537467957},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33559998869895935},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3160000145435333},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2939999997615814},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C176248197","wikidata":"https://www.wikidata.org/wiki/Q458526","display_name":"Probably approximately correct learning","level":4,"score":0.251800000667572}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10458-026-09739-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10458-026-09739-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10458-026-09739-7.pdf","source":{"id":"https://openalex.org/S5405189","display_name":"Autonomous Agents and Multi-Agent Systems","issn_l":"1387-2532","issn":["1387-2532","1573-7454"],"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":"Autonomous Agents and Multi-Agent Systems","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-05563358v1","is_oa":true,"landing_page_url":"https://hal.science/hal-05563358","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"Autonomous Agents and Multi-Agent Systems, 2026, 40 (1), pp.16. ⟨10.1007/s10458-026-09739-7⟩","raw_type":"Journal articles"}],"best_oa_location":{"id":"doi:10.1007/s10458-026-09739-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10458-026-09739-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10458-026-09739-7.pdf","source":{"id":"https://openalex.org/S5405189","display_name":"Autonomous Agents and Multi-Agent Systems","issn_l":"1387-2532","issn":["1387-2532","1573-7454"],"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":"Autonomous Agents and Multi-Agent Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.5651494264602661,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320324252","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7134915135.pdf","grobid_xml":"https://content.openalex.org/works/W7134915135.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W158722652","https://openalex.org/W206679605","https://openalex.org/W1988526405","https://openalex.org/W2096825593","https://openalex.org/W2108005621","https://openalex.org/W2147492008","https://openalex.org/W2165698076","https://openalex.org/W2334782222","https://openalex.org/W2921955147","https://openalex.org/W2968526727","https://openalex.org/W2989934645","https://openalex.org/W3106649810","https://openalex.org/W3156295478","https://openalex.org/W3171954428","https://openalex.org/W3198359393","https://openalex.org/W4246078117","https://openalex.org/W4383112908","https://openalex.org/W4415798324","https://openalex.org/W7133226216"],"related_works":[],"abstract_inverted_index":{"We":[0,59],"present":[1],"an":[2,52],"approach":[3],"for":[4,18],"the":[5,8,31,44,63,68,84,93,103,113],"quantification":[6],"of":[7,10,25,71,79,115],"usefulness":[9],"transfer":[11,119],"in":[12,30,105,118],"reinforcement":[13],"learning":[14],"via":[15],"regret":[16,45,70,104],"bounds":[17,111],"a":[19,23,77],"multi-agent":[20,106],"setting.":[21],"Considering":[22],"number":[24],"$$\\varvec{\\aleph":[26],"}$$":[27],"agents":[28,64,73],"operating":[29],"same":[32],"Markov":[33],"decision":[34],"process,":[35],"however":[36],"possibly":[37],"with":[38,49],"different":[39],"reward":[40],"functions,":[41],"we":[42],"consider":[43],"each":[46,87],"agent":[47,88],"suffers":[48],"respect":[50],"to":[51,83,90],"optimal":[53],"policy":[54],"maximizing":[55],"its":[56],"average":[57],"reward.":[58],"show":[60],"that":[61],"when":[62,86],"share":[65],"their":[66],"observations":[67,117],"mutual":[69],"all":[72],"is":[74],"smaller":[75],"by":[76,96],"factor":[78],"$$\\varvec{\\sqrt{\\aleph":[80],"}}$$":[81],"compared":[82],"case":[85],"has":[89],"rely":[91],"on":[92,112],"information":[94],"collected":[95],"itself.":[97],"This":[98],"result":[99],"demonstrates":[100],"how":[101],"considering":[102],"settings":[107],"can":[108],"provide":[109],"theoretical":[110],"benefit":[114],"sharing":[116],"learning.":[120]},"counts_by_year":[],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2026-03-12T00:00:00"}