{"id":"https://openalex.org/W3095160328","doi":"https://doi.org/10.1109/cdc42340.2020.9303788","title":"Expert Selection in High-Dimensional Markov Decision Processes","display_name":"Expert Selection in High-Dimensional Markov Decision Processes","publication_year":2020,"publication_date":"2020-12-14","ids":{"openalex":"https://openalex.org/W3095160328","doi":"https://doi.org/10.1109/cdc42340.2020.9303788","mag":"3095160328"},"language":"en","primary_location":{"id":"doi:10.1109/cdc42340.2020.9303788","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc42340.2020.9303788","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 59th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2010.15599","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009308827","display_name":"Vicen\u00e7 Rubies-Royo","orcid":"https://orcid.org/0000-0002-8814-0248"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Vicenc Rubies-Royo","raw_affiliation_strings":["University of California, Berkeley, CA","University of California, Department of Electrical Engineering and Computer Science, Berkeley CA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, CA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Department of Electrical Engineering and Computer Science, Berkeley CA#TAB#","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089549365","display_name":"Eric Mazumdar","orcid":"https://orcid.org/0000-0002-1815-269X"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Mazumdar","raw_affiliation_strings":["University of California, Berkeley, CA","University of California, Department of Electrical Engineering and Computer Science, Berkeley CA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, CA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Department of Electrical Engineering and Computer Science, Berkeley CA#TAB#","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002477602","display_name":"Roy Dong","orcid":"https://orcid.org/0000-0001-8034-4329"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roy Dong","raw_affiliation_strings":["University of California, Berkeley, CA","University of California, Department of Electrical Engineering and Computer Science, Berkeley CA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, CA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Department of Electrical Engineering and Computer Science, Berkeley CA#TAB#","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045155646","display_name":"Claire J. Tomlin","orcid":"https://orcid.org/0000-0003-3192-3185"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Claire Tomlin","raw_affiliation_strings":["University of California, Berkeley, CA","University of California, Department of Electrical Engineering and Computer Science, Berkeley CA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, CA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Department of Electrical Engineering and Computer Science, Berkeley CA#TAB#","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103101043","display_name":"S. Shankar Sastry","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. Shankar Sastry","raw_affiliation_strings":["University of California, Berkeley, CA","University of California, Department of Electrical Engineering and Computer Science, Berkeley CA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, CA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Department of Electrical Engineering and Computer Science, Berkeley CA#TAB#","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5009308827"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1714201,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3604","last_page":"3610"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":1.0,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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/T12288","display_name":"Optimization and Search Problems","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/regret","display_name":"Regret","score":0.8017489910125732},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7004894018173218},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6891975402832031},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6538911461830139},{"id":"https://openalex.org/keywords/expert-system","display_name":"Expert system","score":0.6127752065658569},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.556475818157196},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5215411186218262},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5151897668838501},{"id":"https://openalex.org/keywords/expert-elicitation","display_name":"Expert elicitation","score":0.47605133056640625},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.414331316947937},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4120936393737793},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3770412504673004},{"id":"https://openalex.org/keywords/operations-research","display_name":"Operations research","score":0.3539671301841736},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17857128381729126},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13214367628097534},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07676109671592712}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.8017489910125732},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7004894018173218},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6891975402832031},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6538911461830139},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.6127752065658569},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.556475818157196},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5215411186218262},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5151897668838501},{"id":"https://openalex.org/C72161134","wikidata":"https://www.wikidata.org/wiki/Q5421219","display_name":"Expert elicitation","level":2,"score":0.47605133056640625},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.414331316947937},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4120936393737793},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3770412504673004},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.3539671301841736},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17857128381729126},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13214367628097534},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07676109671592712},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/cdc42340.2020.9303788","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc42340.2020.9303788","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 59th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2010.15599","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.15599","pdf_url":"https://arxiv.org/pdf/2010.15599","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},{"id":"mag:3095160328","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2010.15599.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:authors.library.caltech.edu:110733","is_oa":false,"landing_page_url":"https://resolver.caltech.edu/CaltechAUTHORS:20210903-222215578","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Book Section"},{"id":"doi:10.48550/arxiv.2010.15599","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2010.15599","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2010.15599","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.15599","pdf_url":"https://arxiv.org/pdf/2010.15599","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7099999785423279,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1570963478","https://openalex.org/W1651456183","https://openalex.org/W1751431909","https://openalex.org/W1757796397","https://openalex.org/W1998498767","https://openalex.org/W2009551863","https://openalex.org/W2049934117","https://openalex.org/W2119738618","https://openalex.org/W2122187689","https://openalex.org/W2124519059","https://openalex.org/W2132908009","https://openalex.org/W2143101460","https://openalex.org/W2149943599","https://openalex.org/W2238162249","https://openalex.org/W2337024056","https://openalex.org/W2737900586","https://openalex.org/W2949608212","https://openalex.org/W2952099252","https://openalex.org/W2963942401","https://openalex.org/W2963980515","https://openalex.org/W3102381603","https://openalex.org/W4206530644","https://openalex.org/W6627932998","https://openalex.org/W6637967152","https://openalex.org/W6638018090","https://openalex.org/W6679661297","https://openalex.org/W6681292111","https://openalex.org/W6737562511","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W3121118810","https://openalex.org/W2737900586","https://openalex.org/W2331759129","https://openalex.org/W2074902040","https://openalex.org/W1999784270","https://openalex.org/W3092636900","https://openalex.org/W2892787491","https://openalex.org/W2990042081","https://openalex.org/W2972441443","https://openalex.org/W2118902005","https://openalex.org/W2125098603","https://openalex.org/W2355064473","https://openalex.org/W2012287204","https://openalex.org/W2019272477","https://openalex.org/W1487408605","https://openalex.org/W2804817384","https://openalex.org/W2952444386","https://openalex.org/W2602925161","https://openalex.org/W3112347677","https://openalex.org/W2797105841"],"abstract_inverted_index":{"In":[0],"this":[1],"work":[2],"we":[3],"present":[4],"a":[5,27,45],"multi-armed":[6],"bandit":[7],"framework":[8],"for":[9,85],"online":[10],"expert":[11,31,43,72],"selection":[12],"in":[13,21,58,68],"Markov":[14],"decision":[15],"processes":[16],"and":[17,33,77],"demonstrate":[18],"its":[19],"use":[20],"high-dimensional":[22],"settings.":[23],"Our":[24],"method":[25],"takes":[26],"set":[28],"of":[29,47,62],"candidate":[30],"policies":[32,73],"switches":[34],"between":[35],"them":[36],"to":[37,80],"rapidly":[38],"identify":[39],"the":[40,48,59,63,86],"best":[41],"performing":[42],"using":[44],"variant":[46],"classical":[49],"upper":[50],"confidence":[51],"bound":[52],"algorithm,":[53],"thus":[54],"ensuring":[55],"low":[56],"regret":[57],"overall":[60],"performance":[61],"system.":[64],"This":[65],"is":[66],"useful":[67],"applications":[69],"where":[70],"several":[71],"may":[74],"be":[75,81],"available,":[76],"one":[78],"needs":[79],"selected":[82],"at":[83],"run-time":[84],"underlying":[87],"environment.":[88]},"counts_by_year":[],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}
