{"id":"https://openalex.org/W4416618345","doi":"https://doi.org/10.48550/arxiv.2510.20152","title":"Soft Switching Expert Policies for Controlling Systems with Uncertain Parameters","display_name":"Soft Switching Expert Policies for Controlling Systems with Uncertain Parameters","publication_year":2025,"publication_date":"2025-10-23","ids":{"openalex":"https://openalex.org/W4416618345","doi":"https://doi.org/10.48550/arxiv.2510.20152"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2510.20152","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.20152","pdf_url":"https://arxiv.org/pdf/2510.20152","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.20152","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070836427","display_name":"Junya Ikemoto","orcid":"https://orcid.org/0000-0002-0145-3381","observed_orcids":["https://orcid.org/0000-0002-0145-3381"]},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Ikemoto, Junya","raw_affiliation_strings":["Graduate School of Engineering The University of Osaka , 2-1 Yamadaoka , Suita , Osaka , Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering The University of Osaka , 2-1 Yamadaoka , Suita , Osaka , Japan","institution_ids":["https://openalex.org/I98285908"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5070836427"],"corresponding_institution_ids":["https://openalex.org/I98285908"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"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":0.9976000189781189,"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":0.9976000189781189,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0017999999690800905,"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/T11195","display_name":"Simulation Techniques and Applications","score":9.999999747378752e-05,"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/soft-switching","display_name":"soft switching","score":0.7829999923706055},{"id":"https://openalex.org/keywords/reality-gap","display_name":"reality gap","score":0.7319999933242798},{"id":"https://openalex.org/keywords/uncertain-system-parameters","display_name":"uncertain system parameters","score":0.859000027179718},{"id":"https://openalex.org/keywords/online-convex-optimization","display_name":"online convex optimization","score":0.9919999837875366}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7006999850273132},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6657000184059143},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5741999745368958},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.42149999737739563},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.40630000829696655},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.3808000087738037},{"id":"https://openalex.org/C157972887","wikidata":"https://www.wikidata.org/wiki/Q463359","display_name":"Convex optimization","level":3,"score":0.37459999322891235},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3368000090122223},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.3109000027179718},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.2978000044822693},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2799000144004822},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.2786000072956085},{"id":"https://openalex.org/C116672817","wikidata":"https://www.wikidata.org/wiki/Q1454986","display_name":"Physical system","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.2533999979496002}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2510.20152","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.20152","pdf_url":"https://arxiv.org/pdf/2510.20152","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.20152","doi":"https://doi.org/10.48550/arxiv.2510.20152","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.20152","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.20152","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.20152","pdf_url":"https://arxiv.org/pdf/2510.20152","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416618345.pdf","grobid_xml":"https://content.openalex.org/works/W4416618345.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W2173248099","https://openalex.org/W2964121744","https://openalex.org/W3203489455","https://openalex.org/W3210787633"],"related_works":["https://openalex.org/W3108395128","https://openalex.org/W3118961937","https://openalex.org/W3163874881","https://openalex.org/W4407949610","https://openalex.org/W3202665180","https://openalex.org/W3150527705","https://openalex.org/W3014228888","https://openalex.org/W3217653151","https://openalex.org/W3147665045","https://openalex.org/W2615735215"],"abstract_inverted_index":{"This":[0,77],"paper":[1],"proposes":[2],"a":[3,30,39,55,59,92],"simulation-based":[4],"reinforcement":[5],"learning":[6,23,83],"algorithm":[7,73],"for":[8,21,48,58],"controlling":[9],"systems":[10,49],"with":[11,50,86],"uncertain":[12],"and":[13],"varying":[14],"system":[15,52],"parameters.":[16],"While":[17],"simulators":[18],"are":[19,46,65],"useful":[20],"safely":[22],"control":[24,44,63],"policies,":[25],"the":[26,62,97],"reality":[27,98],"gap":[28],"remains":[29],"major":[31],"challenge.":[32],"To":[33],"alleviate":[34],"this":[35],"challenge,":[36],"we":[37],"propose":[38],"two-stage":[40],"algorithm.":[41],"First,":[42],"multiple":[43],"policies":[45,64],"learned":[47],"different":[51],"parameters":[53],"in":[54],"simulator.":[56],"Second,":[57],"real":[60],"system,":[61],"adaptively":[66],"switched":[67],"using":[68],"an":[69],"online":[70],"convex":[71],"optimization":[72],"based":[74],"on":[75,91],"observations.":[76],"approach":[78],"is":[79],"expected":[80],"to":[81,95],"reduce":[82],"complexity":[84],"compared":[85],"existing":[87],"approaches":[88],"that":[89],"rely":[90],"single":[93],"policy":[94],"address":[96],"gap.":[99]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-25T00:00:00"}