{"id":"https://openalex.org/W4415398233","doi":"https://doi.org/10.1109/icdl63968.2025.11204397","title":"Cyclic Exploration and Exploitation in Surprise Minimizing Reinforcement Learning","display_name":"Cyclic Exploration and Exploitation in Surprise Minimizing Reinforcement Learning","publication_year":2025,"publication_date":"2025-09-16","ids":{"openalex":"https://openalex.org/W4415398233","doi":"https://doi.org/10.1109/icdl63968.2025.11204397"},"language":null,"primary_location":{"id":"doi:10.1109/icdl63968.2025.11204397","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdl63968.2025.11204397","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Development and Learning (ICDL)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100669291","display_name":"Kazuo Kubota","orcid":"https://orcid.org/0000-0002-2471-8469"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Kinari Kubota","raw_affiliation_strings":["National Institute of Informatics,Tokyo,Japan,101-8430"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics,Tokyo,Japan,101-8430","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051304187","display_name":"Taisuke Kobayashi","orcid":"https://orcid.org/0000-0002-3760-249X"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Taisuke Kobayashi","raw_affiliation_strings":["National Institute of Informatics,Tokyo,Japan,101-8430"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics,Tokyo,Japan,101-8430","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100669291"],"corresponding_institution_ids":["https://openalex.org/I184597095"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.45021133,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10270","display_name":"Blockchain Technology Applications and Security","score":0.9628999829292297,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10270","display_name":"Blockchain Technology Applications and Security","score":0.9628999829292297,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10328","display_name":"Supply Chain and Inventory Management","score":0.9151999950408936,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7896999716758728},{"id":"https://openalex.org/keywords/surprise","display_name":"Surprise","score":0.7031000256538391},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5789999961853027},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5565000176429749},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.49639999866485596},{"id":"https://openalex.org/keywords/smoothness","display_name":"Smoothness","score":0.4796000123023987},{"id":"https://openalex.org/keywords/inverted-pendulum","display_name":"Inverted pendulum","score":0.45590001344680786},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.4519999921321869}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7896999716758728},{"id":"https://openalex.org/C2780343955","wikidata":"https://www.wikidata.org/wiki/Q333173","display_name":"Surprise","level":2,"score":0.7031000256538391},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5932000279426575},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5789999961853027},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5565000176429749},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.49639999866485596},{"id":"https://openalex.org/C102634674","wikidata":"https://www.wikidata.org/wiki/Q868473","display_name":"Smoothness","level":2,"score":0.4796000123023987},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4595000147819519},{"id":"https://openalex.org/C192921069","wikidata":"https://www.wikidata.org/wiki/Q550134","display_name":"Inverted pendulum","level":3,"score":0.45590001344680786},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.4519999921321869},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35100001096725464},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.35010001063346863},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.3490000069141388},{"id":"https://openalex.org/C2778496695","wikidata":"https://www.wikidata.org/wiki/Q254128","display_name":"Dilemma","level":2,"score":0.34700000286102295},{"id":"https://openalex.org/C125014702","wikidata":"https://www.wikidata.org/wiki/Q4680749","display_name":"Adaptive learning","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.31540000438690186},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.301800012588501},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C167183279","wikidata":"https://www.wikidata.org/wiki/Q1243208","display_name":"Double pendulum","level":4,"score":0.25290000438690186},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdl63968.2025.11204397","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdl63968.2025.11204397","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Development and Learning (ICDL)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0,103],"paper":[1],"addresses":[2],"the":[3,43,77,86,108,120,138],"exploration-exploitation":[4],"dilemma":[5],"in":[6,113,144],"Surprise":[7],"Minimizing":[8],"Reinforcement":[9],"Learning":[10],"(SMiRL)":[11],"by":[12],"introducing":[13],"a":[14,64,71,91,114,126,131],"dynamic":[15],"scaling":[16],"mechanism":[17],"for":[18],"balancing":[19],"intrinsic":[20,38],"and":[21,130,149],"extrinsic":[22],"rewards.":[23],"SMiRL":[24,143],"encourages":[25],"agents":[26],"to":[27,31,48,90,99],"visit":[28],"predictable":[29],"states":[30],"improve":[32],"learning":[33],"stability.":[34],"However,":[35],"its":[36],"pre-specified":[37],"weight":[39],"can":[40],"excessively":[41],"bias":[42],"policy":[44],"toward":[45],"exploitation,":[46],"leading":[47],"inadequate":[49],"exploration":[50,98],"of":[51,110,146],"potentially":[52],"valuable":[53],"but":[54],"initially":[55],"unpredictable":[56],"states.":[57],"To":[58],"alleviate":[59],"this":[60],"issue,":[61],"we":[62],"propose":[63],"novel":[65],"adaptive":[66],"weighting":[67],"framework":[68],"based":[69],"on":[70,123],"latent":[72,116],"amplitude":[73],"metric":[74],"that":[75,137],"indicates":[76],"agent\u2019s":[78],"behavioral":[79],"convergence.":[80],"Our":[81],"method":[82,122,140],"facilitates":[83],"exploitation":[84],"until":[85],"agent":[87],"stably":[88],"converges":[89],"local":[92],"optimum.":[93],"Afterwards,":[94],"it":[95],"triggers":[96],"further":[97],"find":[100],"better":[101],"optima.":[102],"timing":[104],"is":[105],"inferred":[106],"from":[107],"smoothness":[109],"trajectory":[111],"updates":[112],"learned":[115],"space.":[117],"We":[118],"evaluate":[119],"proposed":[121,139],"MuJoCo":[124],"tasks,":[125],"double":[127],"inverted":[128],"pendulum":[129],"quadruped":[132],"locomotion.":[133],"The":[134],"results":[135],"demonstrate":[136],"outperforms":[141],"fixed-weight":[142],"terms":[145],"convergence":[147],"speed":[148],"task-specific":[150],"performance.":[151]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-22T00:00:00"}