{"id":"https://openalex.org/W2914335791","doi":"https://doi.org/10.1109/cdc.2018.8619134","title":"Expedited Learning in MDPs with Side Information","display_name":"Expedited Learning in MDPs with Side Information","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2914335791","doi":"https://doi.org/10.1109/cdc.2018.8619134","mag":"2914335791"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2018.8619134","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2018.8619134","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Conference on Decision and Control (CDC)","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/A5070897457","display_name":"Melkior Ornik","orcid":"https://orcid.org/0000-0002-8510-8787"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Melkior Ornik","raw_affiliation_strings":["Institute for Computational Engineering and Sciences, University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Computational Engineering and Sciences, University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100723531","display_name":"Jie Fu","orcid":"https://orcid.org/0000-0003-3147-6805"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jie Fu","raw_affiliation_strings":["Electrical & Computer Engineering Department, Worcester Polytechnic Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical & Computer Engineering Department, Worcester Polytechnic Institute","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059784141","display_name":"Niklas Lauffer","orcid":"https://orcid.org/0000-0003-2726-5159"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Niklas T. Lauffer","raw_affiliation_strings":["Institute for Computational Engineering and Sciences, University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Computational Engineering and Sciences, University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090200168","display_name":"Withanage K. Perera","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"W. K. Perera","raw_affiliation_strings":["Department of Aerospace Engineering and Engineering Mechanics, University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Aerospace Engineering and Engineering Mechanics, University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007221616","display_name":"Mohammed Alshiekh","orcid":"https://orcid.org/0000-0002-3491-5001"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammed Alshiekh","raw_affiliation_strings":["Institute for Computational Engineering and Sciences, University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Computational Engineering and Sciences, University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101837588","display_name":"Masahiro Ono","orcid":"https://orcid.org/0000-0002-9247-1306"},"institutions":[{"id":"https://openalex.org/I1334627681","display_name":"Jet Propulsion Laboratory","ror":"https://ror.org/027k65916","country_code":"US","type":"facility","lineage":["https://openalex.org/I122411786","https://openalex.org/I1334627681","https://openalex.org/I4210124779"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Masahiro Ono","raw_affiliation_strings":["Jet Propulsion Laboratory, California Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jet Propulsion Laboratory, California Institute of Technology","institution_ids":["https://openalex.org/I1334627681"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068441112","display_name":"Ufuk Topcu","orcid":"https://orcid.org/0000-0003-0819-9985"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ufuk Topcu","raw_affiliation_strings":["Department of Aerospace Engineering and Engineering Mechanics, University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Aerospace Engineering and Engineering Mechanics, University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6758,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.78897796,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"10","issue":null,"first_page":"1941","last_page":"1948"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9959999918937683,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9959999918937683,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.995199978351593,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.984499990940094,"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/computer-science","display_name":"Computer science","score":0.7215144634246826},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.6993807554244995},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6892410516738892},{"id":"https://openalex.org/keywords/transition","display_name":"Transition (genetics)","score":0.6030569076538086},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.593738317489624},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5265745520591736},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5239039659500122},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.47247809171676636},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.46237891912460327},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4340669810771942},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42364057898521423},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3912351131439209},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3054828345775604},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18087685108184814},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.13301092386245728}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7215144634246826},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.6993807554244995},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6892410516738892},{"id":"https://openalex.org/C194232998","wikidata":"https://www.wikidata.org/wiki/Q1606712","display_name":"Transition (genetics)","level":3,"score":0.6030569076538086},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.593738317489624},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5265745520591736},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5239039659500122},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.47247809171676636},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.46237891912460327},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4340669810771942},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42364057898521423},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3912351131439209},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3054828345775604},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18087685108184814},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13301092386245728},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc.2018.8619134","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2018.8619134","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1554944419","https://openalex.org/W1582866771","https://openalex.org/W1594563152","https://openalex.org/W1965522621","https://openalex.org/W1973749534","https://openalex.org/W1975867865","https://openalex.org/W1977543377","https://openalex.org/W1988526405","https://openalex.org/W2013928382","https://openalex.org/W2103012681","https://openalex.org/W2123447947","https://openalex.org/W2124352385","https://openalex.org/W2159178228","https://openalex.org/W2161966552","https://openalex.org/W2171033594","https://openalex.org/W2489939061","https://openalex.org/W2506342991","https://openalex.org/W2587137473","https://openalex.org/W2963778636","https://openalex.org/W3148557096","https://openalex.org/W4233413206","https://openalex.org/W4285719527","https://openalex.org/W6635036405","https://openalex.org/W6678481081","https://openalex.org/W6683603353"],"related_works":["https://openalex.org/W4388311650","https://openalex.org/W5922282","https://openalex.org/W2379651310","https://openalex.org/W2113019827","https://openalex.org/W1541249122","https://openalex.org/W2413828414","https://openalex.org/W2367222340","https://openalex.org/W187740018","https://openalex.org/W2162286586","https://openalex.org/W4255368532"],"abstract_inverted_index":{"Standard":[0],"methods":[1,26],"for":[2],"synthesis":[3],"of":[4,20,36,111,124,176,198,209],"control":[5,51,216],"policies":[6],"in":[7,188,218],"Markov":[8],"decision":[9],"processes":[10],"with":[11,167],"unknown":[12],"transition":[13,87,99,135,147,177,190],"probabilities":[14,88,100,148],"largely":[15],"rely":[16],"on":[17,31,77,82,173],"a":[18,49,61,65,94,102,114,214],"combination":[19],"exploration":[21],"and":[22,39,206],"exploitation.":[23],"While":[24,179],"these":[25],"often":[27],"offer":[28],"theoretical":[29],"guarantees":[30],"system":[32],"performance,":[33],"the":[34,45,83,86,98,138,170,174,180,199,207,219],"number":[35,208],"time":[37],"steps":[38,210],"samples":[40,162],"needed":[41,211],"to":[42,132,169,186,212],"initially":[43],"explore":[44],"environment":[46],"before":[47],"synthesizing":[48],"well-performing":[50],"policy":[52,217],"is":[53,74,142],"impractically":[54],"large.":[55],"This":[56],"paper":[57],"partially":[58],"alleviates":[59],"such":[60,72,201],"burden":[62],"by":[63,195],"incorporating":[64],"priori":[66],"existing":[67],"knowledge":[68,73],"into":[69],"learning,":[70],"when":[71],"available.":[75],"Based":[76],"prior":[78],"information":[79,141,153],"about":[80],"bounds":[81,172],"differences":[84,175],"between":[85],"at":[89,101,117,127,145],"different":[90,160],"states,":[91,161],"we":[92,192],"propose":[93],"learning":[95],"approach":[96],"where":[97],"given":[103],"state":[104],"are":[105,130,165],"not":[106],"only":[107],"learned":[108,189],"from":[109,122,155],"outcomes":[110,123],"repeatedly":[112],"performing":[113,125],"certain":[115],"action":[116],"that":[118,129],"state,":[119],"but":[120,157],"also":[121],"actions":[126],"states":[128],"known":[131,171],"have":[133],"similar":[134,156],"probabilities.":[136,178],"Since":[137],"directly":[139],"obtained":[140,154,163],"more":[143],"reliable":[144],"determining":[146],"than":[149],"second-hand":[150],"information,":[151],"i.e.,":[152],"potentially":[158],"slightly":[159],"indirectly":[164],"weighted":[166],"respect":[168],"proposed":[181],"strategy":[182],"can":[183,203,222],"naturally":[184],"lead":[185],"errors":[187,202],"probabilities,":[191],"show":[193],"that,":[194],"proper":[196],"choice":[197],"weights,":[200],"be":[204,223],"reduced,":[205],"form":[213],"near-optimal":[215],"Bayesian":[220],"sense":[221],"significantly":[224],"decreased.":[225]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}