{"id":"https://openalex.org/W7134832369","doi":"https://doi.org/10.1007/s00422-026-01037-5","title":"A bio-inspired minimal model for non-stationary K-armed bandits","display_name":"A bio-inspired minimal model for non-stationary K-armed bandits","publication_year":2026,"publication_date":"2026-03-10","ids":{"openalex":"https://openalex.org/W7134832369","doi":"https://doi.org/10.1007/s00422-026-01037-5","pmid":"https://pubmed.ncbi.nlm.nih.gov/41806178"},"language":"en","primary_location":{"id":"doi:10.1007/s00422-026-01037-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00422-026-01037-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00422-026-01037-5.pdf","source":{"id":"https://openalex.org/S87357125","display_name":"Biological Cybernetics","issn_l":"0340-1200","issn":["0340-1200","1432-0770"],"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":"Biological Cybernetics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s00422-026-01037-5.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128667131","display_name":"Krubeal Danieli","orcid":null},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Krubeal Danieli","raw_affiliation_strings":["Center for Integrative Neuroplasticity, FYSCELL, University of Oslo, Oslo, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Integrative Neuroplasticity, FYSCELL, University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076471339","display_name":"Mikkel Elle Lepper\u00f8d","orcid":"https://orcid.org/0000-0002-4262-5549"},"institutions":[{"id":"https://openalex.org/I2799829267","display_name":"Simula Research Laboratory","ror":"https://ror.org/00vn06n10","country_code":"NO","type":"facility","lineage":["https://openalex.org/I2799829267"]}],"countries":["NO"],"is_corresponding":true,"raw_author_name":"Mikkel Elle Lepper\u00f8d","raw_affiliation_strings":["Simula Research Laboratory, Oslo, Norway. mikkel@simula.no"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Simula Research Laboratory, Oslo, Norway. mikkel@simula.no","institution_ids":["https://openalex.org/I2799829267"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5076471339"],"corresponding_institution_ids":["https://openalex.org/I2799829267"],"apc_list":{"value":2790,"currency":"EUR","value_usd":3590},"apc_paid":{"value":2790,"currency":"EUR","value_usd":3590},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.42216016,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"120","issue":"2","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.24480000138282776,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.24480000138282776,"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":0.19550000131130219,"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":0.05790000036358833,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.6107000112533569},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.5939000248908997},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5169000029563904},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4408999979496002},{"id":"https://openalex.org/keywords/thompson-sampling","display_name":"Thompson sampling","score":0.36890000104904175},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.32659998536109924}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6323000192642212},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6230999827384949},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6107000112533569},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.5939000248908997},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5169000029563904},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4408999979496002},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43630000948905945},{"id":"https://openalex.org/C73602740","wikidata":"https://www.wikidata.org/wiki/Q7795822","display_name":"Thompson sampling","level":3,"score":0.36890000104904175},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.32659998536109924},{"id":"https://openalex.org/C47822265","wikidata":"https://www.wikidata.org/wiki/Q854457","display_name":"Complex system","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C204983608","wikidata":"https://www.wikidata.org/wiki/Q2111958","display_name":"Productivity","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.26739999651908875},{"id":"https://openalex.org/C120822770","wikidata":"https://www.wikidata.org/wiki/Q5156355","display_name":"Competitive learning","level":3,"score":0.2603999972343445},{"id":"https://openalex.org/C125014702","wikidata":"https://www.wikidata.org/wiki/Q4680749","display_name":"Adaptive learning","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C159149176","wikidata":"https://www.wikidata.org/wiki/Q14489129","display_name":"Evolutionary algorithm","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C2778402161","wikidata":"https://www.wikidata.org/wiki/Q2121931","display_name":"Anterior cingulate cortex","level":3,"score":0.25450000166893005}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D008959","descriptor_name":"Models, Neurological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008959","descriptor_name":"Models, Neurological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008959","descriptor_name":"Models, Neurological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009474","descriptor_name":"Neurons","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D009474","descriptor_name":"Neurons","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D009474","descriptor_name":"Neurons","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1007/s00422-026-01037-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00422-026-01037-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00422-026-01037-5.pdf","source":{"id":"https://openalex.org/S87357125","display_name":"Biological Cybernetics","issn_l":"0340-1200","issn":["0340-1200","1432-0770"],"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":"Biological Cybernetics","raw_type":"journal-article"},{"id":"pmid:41806178","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41806178","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Biological cybernetics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:12975818","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12975818/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"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":"Biol Cybern","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1007/s00422-026-01037-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00422-026-01037-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00422-026-01037-5.pdf","source":{"id":"https://openalex.org/S87357125","display_name":"Biological Cybernetics","issn_l":"0340-1200","issn":["0340-1200","1432-0770"],"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":"Biological Cybernetics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6854747533798218,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320323260","display_name":"Universitetet i Oslo","ror":"https://ror.org/01xtthb56"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7134832369.pdf","grobid_xml":"https://content.openalex.org/works/W7134832369.grobid-xml"},"referenced_works_count":70,"referenced_works":["https://openalex.org/W124449151","https://openalex.org/W1147225692","https://openalex.org/W1968436161","https://openalex.org/W1978837788","https://openalex.org/W1990068200","https://openalex.org/W1996071658","https://openalex.org/W2001971840","https://openalex.org/W2020470595","https://openalex.org/W2024500760","https://openalex.org/W2037917209","https://openalex.org/W2044724603","https://openalex.org/W2056989262","https://openalex.org/W2073869576","https://openalex.org/W2078631477","https://openalex.org/W2085064882","https://openalex.org/W2086244298","https://openalex.org/W2088222816","https://openalex.org/W2093946971","https://openalex.org/W2117342733","https://openalex.org/W2118125647","https://openalex.org/W2123419686","https://openalex.org/W2123429050","https://openalex.org/W2126900474","https://openalex.org/W2129386380","https://openalex.org/W2141114982","https://openalex.org/W2152548506","https://openalex.org/W2158130856","https://openalex.org/W2159088729","https://openalex.org/W2160088187","https://openalex.org/W2161565319","https://openalex.org/W2165116114","https://openalex.org/W2165196764","https://openalex.org/W2166158223","https://openalex.org/W2168405694","https://openalex.org/W2168814611","https://openalex.org/W2181627316","https://openalex.org/W2185095108","https://openalex.org/W2286419477","https://openalex.org/W2342021942","https://openalex.org/W2419438565","https://openalex.org/W2419461529","https://openalex.org/W2514548734","https://openalex.org/W2522517952","https://openalex.org/W2525444040","https://openalex.org/W2599349366","https://openalex.org/W2606776585","https://openalex.org/W2737805006","https://openalex.org/W2738724892","https://openalex.org/W2797393690","https://openalex.org/W2801251491","https://openalex.org/W2810188887","https://openalex.org/W2953162696","https://openalex.org/W3006471948","https://openalex.org/W3023212902","https://openalex.org/W3024348208","https://openalex.org/W3034963871","https://openalex.org/W3046597750","https://openalex.org/W3125634603","https://openalex.org/W3138288323","https://openalex.org/W3139192017","https://openalex.org/W3171739383","https://openalex.org/W4285247025","https://openalex.org/W4293462124","https://openalex.org/W4309317106","https://openalex.org/W4376598554","https://openalex.org/W4385741981","https://openalex.org/W4395066700","https://openalex.org/W4396760778","https://openalex.org/W4399767795","https://openalex.org/W4402215325"],"related_works":[],"abstract_inverted_index":{"While":[0],"reinforcement":[1],"learning":[2,112],"algorithms":[3,61],"have":[4],"made":[5],"significant":[6],"progress":[7],"in":[8,18,77,105],"solving":[9],"multi-armed":[10],"bandit":[11,54],"problems,":[12,55],"they":[13],"often":[14],"lack":[15],"biological":[16],"plausibility":[17],"architecture":[19],"and":[20,42,66,111],"dynamics.":[21],"Here,":[22],"we":[23],"propose":[24],"a":[25],"bio-inspired":[26],"neural":[27,109,130],"model":[28,47,70],"based":[29],"on":[30],"interacting":[31],"populations":[32],"of":[33,59,101,107,132],"rate":[34,113],"neurons,":[35],"drawing":[36],"inspiration":[37],"from":[38],"the":[39,57,69,90,99],"orbitofrontal":[40],"cortex":[41],"anterior":[43],"cingulate":[44],"cortex.":[45],"Our":[46],"reports":[48],"robust":[49],"performance":[50,125],"across":[51],"various":[52],"stochastic":[53],"matching":[56],"effectiveness":[58],"standard":[60],"such":[62],"as":[63,84],"Thompson":[64],"Sampling":[65],"UCB.":[67],"Notably,":[68],"exhibits":[71],"adaptive":[72],"behavior:":[73],"employing":[74],"greedy":[75],"strategies":[76],"low-uncertainty":[78],"situations":[79],"while":[80,126],"increasing":[81],"exploratory":[82],"behavior":[83],"uncertainty":[85],"rises.":[86],"Through":[87],"evolutionary":[88],"optimization,":[89],"model's":[91],"hyperparameters":[92],"converged":[93],"to":[94],"values":[95],"that":[96,118],"align":[97],"with":[98],"principles":[100],"synaptic":[102],"mechanisms,":[103],"particularly":[104],"terms":[106],"synapse-dependent":[108],"activity":[110],"adaptation.":[114],"These":[115],"findings":[116],"suggest":[117],"biologically-inspired":[119],"computational":[120],"architectures":[121],"can":[122],"achieve":[123],"competitive":[124],"providing":[127],"insights":[128],"into":[129],"mechanisms":[131],"decision-making":[133],"under":[134],"uncertainty.":[135]},"counts_by_year":[],"updated_date":"2026-05-09T13:55:54.758798","created_date":"2026-03-11T00:00:00"}