{"id":"https://openalex.org/W3046018659","doi":"https://doi.org/10.23919/acc45564.2020.9147372","title":"Safety-Guaranteed, Accelerated Learning in MDPs with Local Side Information","display_name":"Safety-Guaranteed, Accelerated Learning in MDPs with Local Side Information","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3046018659","doi":"https://doi.org/10.23919/acc45564.2020.9147372","mag":"3046018659","pmid":"https://pubmed.ncbi.nlm.nih.gov/33223606"},"language":"en","primary_location":{"id":"doi:10.23919/acc45564.2020.9147372","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc45564.2020.9147372","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 American Control Conference (ACC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7676387","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023184269","display_name":"Pranay Thangeda","orcid":"https://orcid.org/0000-0002-0680-6334"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pranay Thangeda","raw_affiliation_strings":["Department of Aerospace Engineering and the Coordinated Science Laboratory, University of Illinois at Urbana-Champaign, Urbana, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Aerospace Engineering and the Coordinated Science Laboratory, University of Illinois at Urbana-Champaign, Urbana, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070897457","display_name":"Melkior Ornik","orcid":"https://orcid.org/0000-0002-8510-8787"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Melkior Ornik","raw_affiliation_strings":["Department of Aerospace Engineering and the Coordinated Science Laboratory, University of Illinois at Urbana-Champaign, Urbana, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Aerospace Engineering and the Coordinated Science Laboratory, University of Illinois at Urbana-Champaign, Urbana, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1354,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.55298509,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"2020","issue":null,"first_page":"1099","last_page":"1104"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9975000023841858,"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":0.9975000023841858,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9805999994277954,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9664999842643738,"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/markov-decision-process","display_name":"Markov decision process","score":0.8390921354293823},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.755535364151001},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6597132682800293},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6148448586463928},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.46868613362312317},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4598328769207001},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44449788331985474},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.434237539768219},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43170303106307983},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.41202571988105774},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4025510549545288},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3784927725791931},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1142403781414032},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.09236708283424377}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8390921354293823},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.755535364151001},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6597132682800293},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6148448586463928},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.46868613362312317},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4598328769207001},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44449788331985474},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.434237539768219},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43170303106307983},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.41202571988105774},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4025510549545288},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3784927725791931},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1142403781414032},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.09236708283424377},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.23919/acc45564.2020.9147372","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc45564.2020.9147372","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 American Control Conference (ACC)","raw_type":"proceedings-article"},{"id":"pmid:33223606","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33223606","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":"Proceedings of the ... American Control Conference. American Control Conference","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:7676387","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7676387","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc Am Control Conf","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:7676387","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7676387","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc Am Control Conf","raw_type":"Text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1975867865","https://openalex.org/W2003048154","https://openalex.org/W2029578340","https://openalex.org/W2103012681","https://openalex.org/W2119567691","https://openalex.org/W2123447947","https://openalex.org/W2124352385","https://openalex.org/W2131288186","https://openalex.org/W2137351138","https://openalex.org/W2151237105","https://openalex.org/W2161966552","https://openalex.org/W2489939061","https://openalex.org/W2618318883","https://openalex.org/W2890848579","https://openalex.org/W2914335791","https://openalex.org/W2963575966","https://openalex.org/W4214587036","https://openalex.org/W4233413206","https://openalex.org/W4233840023","https://openalex.org/W4285719527","https://openalex.org/W4294555834","https://openalex.org/W4297780563","https://openalex.org/W6657961498","https://openalex.org/W6678481081","https://openalex.org/W6680367670","https://openalex.org/W6682367392","https://openalex.org/W6683603353","https://openalex.org/W6738483526"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W4284974072","https://openalex.org/W2341346307","https://openalex.org/W4404955202"],"abstract_inverted_index":{"In":[0],"environments":[1],"with":[2,98,186,214],"uncertain":[3],"dynamics,":[4],"synthesis":[5,147],"of":[6,14,27,47,61,85,88,93,105,114,133,148,158,170,182,210],"optimal":[7,150],"control":[8,151],"policies":[9],"mandates":[10],"exploration.":[11],"The":[12],"applicability":[13],"classical":[15],"learning":[16,32,66,143,202],"algorithms":[17],"to":[18,67],"real-world":[19],"problems":[20],"is":[21],"often":[22],"limited":[23],"by":[24,81,117],"the":[25,33,42,48,53,59,83,86,91,106,110,130,142,149,156,168,180,199,208,221],"number":[26],"time":[28,138],"steps":[29],"required":[30],"for":[31,64,164],"environment":[34],"model.":[35],"Given":[36],"some":[37],"local":[38,125,191,222],"side":[39,126,192,223],"information":[40,89,127,135],"about":[41],"differences":[43],"in":[44,90,109,167,201,207],"transition":[45,100,115],"probabilities":[46,116],"states,":[49],"potentially":[50],"obtained":[51],"from":[52,216],"agent's":[54,111],"onboard":[55,217],"sensors,":[56],"we":[57,140,154,176],"generalize":[58],"idea":[60,80],"indirect":[62],"sampling":[63],"accelerated":[65],"propose":[68],"an":[69,183],"algorithm":[70,188],"that":[71,189],"balances":[72],"between":[73],"exploration":[74],"and":[75,128,145,198],"exploitation.":[76],"We":[77,194],"formalize":[78],"this":[79],"introducing":[82],"notion":[84,157],"value":[87,132],"context":[92,169],"a":[94,103,119,161,211],"Markov":[95],"decision":[96],"process":[97,144],"unknown":[99],"probabilities,":[101],"as":[102,220],"measure":[104],"expected":[107],"improvement":[108,200],"current":[112],"estimate":[113],"taking":[118],"particular":[120],"action.":[121],"By":[122],"exploiting":[123],"available":[124],"maximizing":[129],"estimated":[131],"learned":[134],"at":[136],"each":[137],"step,":[139],"accelerate":[141],"subsequent":[146],"policy.":[152],"Further,":[153],"define":[155],"agent":[159,184,196],"safety,":[160],"vital":[162],"consideration":[163],"physical":[165],"systems,":[166],"our":[171,187],"problem.":[172],"Under":[173],"certain":[174],"assumptions,":[175],"provide":[177],"guarantees":[178],"on":[179],"safety":[181,197],"exploring":[185],"exploits":[190],"information.":[193,224],"illustrate":[195],"speed":[203],"using":[204],"numerical":[205],"experiments":[206],"setting":[209],"Mars":[212],"rover,":[213],"data":[215],"sensors":[218],"acting":[219]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
