{"id":"https://openalex.org/W7160201658","doi":"https://doi.org/10.1007/s10458-026-09748-6","title":"$$\\varepsilon $$-retraining reinforcement learning algorithms","display_name":"$$\\varepsilon $$-retraining reinforcement learning algorithms","publication_year":2026,"publication_date":"2026-05-04","ids":{"openalex":"https://openalex.org/W7160201658","doi":"https://doi.org/10.1007/s10458-026-09748-6"},"language":"en","primary_location":{"id":"doi:10.1007/s10458-026-09748-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10458-026-09748-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10458-026-09748-6.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/s10458-026-09748-6.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005034849","display_name":"Luca Marzari","orcid":"https://orcid.org/0000-0002-0069-0182"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Luca Marzari","raw_affiliation_strings":["TU Wien, Vienna, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Wien, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135253296","display_name":"Changliu Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Changliu Liu","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075620331","display_name":"Priya L. Donti","orcid":"https://orcid.org/0000-0002-8503-7464"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Priya L. Donti","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135189244","display_name":"Enrico Marchesini","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Enrico Marchesini","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5005034849"],"corresponding_institution_ids":["https://openalex.org/I145847075"],"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":0.80566393,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8701000213623047,"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":0.8701000213623047,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.015799999237060547,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.010200000368058681,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.8334000110626221},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6712999939918518},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4551999866962433},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.44530001282691956},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4388999938964844},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.42419999837875366},{"id":"https://openalex.org/keywords/retraining","display_name":"Retraining","score":0.42289999127388},{"id":"https://openalex.org/keywords/monotonic-function","display_name":"Monotonic function","score":0.41659998893737793}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8334000110626221},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6712999939918518},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.647599995136261},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5034000277519226},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4551999866962433},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.44530001282691956},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4388999938964844},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.42419999837875366},{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.42289999127388},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.41659998893737793},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.39660000801086426},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38749998807907104},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37119999527931213},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.36309999227523804},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.35420000553131104},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.3540000021457672},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3197999894618988},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.3037000000476837},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10458-026-09748-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10458-026-09748-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10458-026-09748-6.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"}],"best_oa_location":{"id":"doi:10.1007/s10458-026-09748-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10458-026-09748-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10458-026-09748-6.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":[{"id":"https://metadata.un.org/sdg/16","score":0.4114062488079071,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7160201658.pdf","grobid_xml":"https://content.openalex.org/works/W7160201658.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1507872748","https://openalex.org/W2123447947","https://openalex.org/W2746553466","https://openalex.org/W2796290181","https://openalex.org/W2971115780","https://openalex.org/W3003931103","https://openalex.org/W3018036994","https://openalex.org/W3119977777","https://openalex.org/W3137465606","https://openalex.org/W4200342431","https://openalex.org/W4205950066","https://openalex.org/W4233413206","https://openalex.org/W4285600796","https://openalex.org/W4301014524","https://openalex.org/W4383108795","https://openalex.org/W4385767377","https://openalex.org/W4393146543","https://openalex.org/W4401415577","https://openalex.org/W4412514823","https://openalex.org/W4413017482","https://openalex.org/W4414654073","https://openalex.org/W4415798733","https://openalex.org/W4416060036","https://openalex.org/W7133193934","https://openalex.org/W7139075321"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"We":[1,84],"present":[2],"$$\\varepsilon":[3,30,67,111,148],"$$":[4,31,68,112,149],",":[5],"a":[6,33,48,64,151],"general":[7],"exploration":[8],"strategy":[9],"for":[10,88,156],"reinforcement":[11],"learning":[12],"(RL)":[13],"that":[14],"encourages":[15],"adherence":[16,135],"to":[17,63,123],"behavioral":[18,134,158],"preferences":[19,159],"while":[20],"preserving":[21],"the":[22,26,40,44,52,77,81,86,137],"convergence":[23,114],"guarantees":[24],"of":[25,36,39],"underlying":[27],"RL":[28,127],"algorithm.":[29],"maintains":[32],"dynamic":[34],"collection":[35],"retrain":[37],"areas\u2014regions":[38],"state":[41],"space":[42],"where":[43],"agent":[45],"previously":[46],"violated":[47],"specified":[49],"preference\u2014and":[50],"mixes":[51],"standard":[53],"uniform":[54],"restart":[55],"distribution":[56],"with":[57],"states":[58],"from":[59],"these":[60],"areas,":[61],"according":[62],"decaying":[65],"parameter":[66],".":[69],"This":[70],"mixed":[71],"retraining":[72],"thus":[73],"focuses":[74],"on":[75],"enforcing":[76],"desired":[78],"behaviors":[79],"in":[80,97,108,136],"collected":[82],"areas.":[83],"develop":[85],"theory":[87],"both":[89],"policy":[90],"and":[91,106,129,133,141],"value-based":[92,109],"methods,":[93],"showing":[94],"that:":[95],"(i)":[96],"policy-based":[98],"settings,":[99,110],"our":[100],"method":[101],"retains":[102],"monotonic":[103],"improvement":[104],"bounds;":[105],"(ii)":[107],"preserves":[113],"properties":[115],"without":[116],"additional":[117],"assumptions.":[118],"The":[119],"approach":[120],"is":[121],"simple":[122],"integrate":[124],"into":[125,160],"existing":[126],"algorithms":[128],"improves":[130],"sample":[131],"efficiency":[132],"locomotion,":[138],"power":[139],"systems,":[140],"navigation":[142],"tasks":[143],"tested.":[144],"These":[145],"results":[146],"establish":[147],"as":[150],"lightweight,":[152],"theoretically":[153],"grounded":[154],"mechanism":[155],"incorporating":[157],"RL.":[161]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-05-05T00:00:00"}