{"id":"https://openalex.org/W4414433632","doi":"https://doi.org/10.1109/case58245.2025.11163912","title":"Bounded Active Exploration for Model-Based Reinforcement Learning","display_name":"Bounded Active Exploration for Model-Based Reinforcement Learning","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4414433632","doi":"https://doi.org/10.1109/case58245.2025.11163912"},"language":"en","primary_location":{"id":"doi:10.1109/case58245.2025.11163912","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case58245.2025.11163912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 21st International Conference on Automation Science and Engineering (CASE)","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/A5007950970","display_name":"Ting Qiao","orcid":null},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":true,"raw_author_name":"Ting Qiao","raw_affiliation_strings":["The University of Auckland,Centre for Automation and Robotic Engineering Science,New Zealand"],"affiliations":[{"raw_affiliation_string":"The University of Auckland,Centre for Automation and Robotic Engineering Science,New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054709242","display_name":"Henry Williams","orcid":"https://orcid.org/0000-0003-4510-0219"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Henry Williams","raw_affiliation_strings":["The University of Auckland,Centre for Automation and Robotic Engineering Science,New Zealand"],"affiliations":[{"raw_affiliation_string":"The University of Auckland,Centre for Automation and Robotic Engineering Science,New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065146109","display_name":"Bruce A. MacDonald","orcid":"https://orcid.org/0000-0001-7602-8497"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Bruce A. MacDonald","raw_affiliation_strings":["The University of Auckland,Centre for Automation and Robotic Engineering Science,New Zealand"],"affiliations":[{"raw_affiliation_string":"The University of Auckland,Centre for Automation and Robotic Engineering Science,New Zealand","institution_ids":["https://openalex.org/I154130895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5007950970"],"corresponding_institution_ids":["https://openalex.org/I154130895"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34315197,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2180","last_page":"2187"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9919000267982483,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9919000267982483,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11801","display_name":"Reservoir Engineering and Simulation Methods","score":0.9710000157356262,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11053","display_name":"Process Optimization and Integration","score":0.9441999793052673,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8260999917984009},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.54830002784729},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5404999852180481},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.3732999861240387},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.33719998598098755}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8260999917984009},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6154999732971191},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.54830002784729},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5404999852180481},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5339999794960022},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.3732999861240387},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3668999969959259},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.33719998598098755},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.2921000123023987}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/case58245.2025.11163912","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case58245.2025.11163912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 21st International Conference on Automation Science and Engineering (CASE)","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":13,"referenced_works":["https://openalex.org/W1988526405","https://openalex.org/W2163922914","https://openalex.org/W2489939061","https://openalex.org/W2962872206","https://openalex.org/W3018268080","https://openalex.org/W3183048323","https://openalex.org/W3207342878","https://openalex.org/W4214717370","https://openalex.org/W4220747123","https://openalex.org/W4402402057","https://openalex.org/W4405785262","https://openalex.org/W4405787930","https://openalex.org/W4407822334"],"related_works":[],"abstract_inverted_index":{"A":[0],"precise":[1],"world":[2,17,26,45],"model":[3,27],"is":[4],"imperative":[5],"for":[6,134],"the":[7,25,77,109],"performance":[8],"of":[9,111],"Model-Based":[10],"Reinforcement":[11,139],"Learning":[12],"(MBRL).":[13],"Active":[14],"exploration":[15,56,61,65,114],"enhances":[16],"models":[18],"via":[19],"repeatedly":[20],"visiting":[21],"uncertain":[22],"regions":[23],"where":[24],"lacks":[28],"proficiency.":[29],"However,":[30],"this":[31,50],"strategy":[32,115],"may":[33],"introduce":[34],"an":[35,43,131],"objective":[36],"mismatch":[37],"between":[38],"maximising":[39],"rewards":[40],"and":[41,102],"developing":[42],"accurate":[44],"model.":[46],"In":[47],"response":[48],"to":[49],"challenge,":[51],"we":[52],"propose":[53],"a":[54,72],"novel":[55,113],"strategy,":[57],"termed":[58],"bounded":[59],"active":[60],"(BAE),":[62],"that":[63],"confines":[64],"behaviours":[66],"within":[67],"action":[68],"candidates":[69,82],"derived":[70],"from":[71,94],"soft":[73],"reward-exploitation":[74],"policy.":[75],"As":[76],"policy":[78],"becomes":[79],"\u2018confident\u2019,":[80],"these":[81],"converge":[83],"on":[84,100],"one":[85],"single":[86],"decisive":[87],"action.":[88],"We":[89],"evaluate":[90],"BAE":[91,120],"with":[92],"algorithms":[93],"two":[95],"disparate":[96],"MBRL":[97,124],"research":[98],"streams":[99],"simulation":[101,118],"real-world":[103],"tasks.":[104,119],"The":[105],"empirical":[106],"results":[107],"manifest":[108],"superiority":[110],"our":[112],"in":[116,138],"most":[117],"not":[121],"only":[122],"elevates":[123],"agents\u2019":[125],"data":[126],"efficiency":[127],"but":[128],"also":[129],"provides":[130],"alternative":[132],"method":[133],"applying":[135],"intrinsic":[136],"motivations":[137],"Learning.":[140]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}