{"id":"https://openalex.org/W4381551344","doi":"https://doi.org/10.48550/arxiv.2306.10259","title":"Active Policy Improvement from Multiple Black-box Oracles","display_name":"Active Policy Improvement from Multiple Black-box Oracles","publication_year":2023,"publication_date":"2023-06-17","ids":{"openalex":"https://openalex.org/W4381551344","doi":"https://doi.org/10.48550/arxiv.2306.10259"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2306.10259","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.10259","pdf_url":"https://arxiv.org/pdf/2306.10259","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":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2306.10259","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100400563","display_name":"Xuefeng Liu","orcid":"https://orcid.org/0000-0003-2705-8731"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Liu, Xuefeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086678121","display_name":"Takuma Yoneda","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yoneda, Takuma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104252950","display_name":"Chaoqi Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Chaoqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103153703","display_name":"Matthew R. Walter","orcid":"https://orcid.org/0000-0003-1425-6050"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Walter, Matthew R.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100416078","display_name":"Yuxin Chen","orcid":"https://orcid.org/0000-0001-9256-5815"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yuxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100400563"],"corresponding_institution_ids":[],"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":0.9952999949455261,"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":0.9952999949455261,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9616000056266785,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.95169997215271,"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/oracle","display_name":"Oracle","score":0.8891726732254028},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.792579174041748},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7526099681854248},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.6401959657669067},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.5777666568756104},{"id":"https://openalex.org/keywords/black-box","display_name":"Black box","score":0.5227320790290833},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4840235412120819},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.46834322810173035},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.453289270401001},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.44601184129714966},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.44306427240371704},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4284050464630127},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.41311872005462646},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12912920117378235},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.1252976357936859},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08029374480247498}],"concepts":[{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.8891726732254028},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.792579174041748},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7526099681854248},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.6401959657669067},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.5777666568756104},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.5227320790290833},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4840235412120819},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.46834322810173035},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.453289270401001},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.44601184129714966},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.44306427240371704},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4284050464630127},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.41311872005462646},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12912920117378235},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.1252976357936859},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08029374480247498},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2306.10259","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.10259","pdf_url":"https://arxiv.org/pdf/2306.10259","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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2306.10259","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2306.10259","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:2306.10259","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.10259","pdf_url":"https://arxiv.org/pdf/2306.10259","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":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.47999998927116394,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1489425746","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G1527848044","display_name":null,"funder_award_id":"89233218CNA000001","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G1645119126","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G1751644051","display_name":null,"funder_award_id":"DE-AC02-06CH11357","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G2777053550","display_name":null,"funder_award_id":"AC02-06CH11357","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G3232922872","display_name":null,"funder_award_id":"17-SC-20-SC","funder_id":"https://openalex.org/F4320332369","funder_display_name":"National Nuclear Security Administration"},{"id":"https://openalex.org/G3318903820","display_name":null,"funder_award_id":"DE-AC02-06CH11357","funder_id":"https://openalex.org/F4320332369","funder_display_name":"National Nuclear Security Administration"},{"id":"https://openalex.org/G3679317512","display_name":"Institute for Data, Econometrics, Algorithms and Learning (IDEAL)","funder_award_id":"2216899","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4327825534","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320332369","funder_display_name":"National Nuclear Security Administration"},{"id":"https://openalex.org/G498139845","display_name":null,"funder_award_id":"DE-AC02","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G574795485","display_name":null,"funder_award_id":"DE-AC52-07NA27344","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G5783643890","display_name":null,"funder_award_id":"DE-AC02-06-CH11357","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G5816449448","display_name":null,"funder_award_id":"DE-AC52-07NA27344","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6495930337","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6558272803","display_name":null,"funder_award_id":"DE-AC02","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6848031779","display_name":null,"funder_award_id":"06CH11357","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6859237865","display_name":null,"funder_award_id":"17-SC-20-SC","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6918803902","display_name":null,"funder_award_id":"06CH11357","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G6995210142","display_name":null,"funder_award_id":"89233218CNA000001","funder_id":"https://openalex.org/F4320332369","funder_display_name":"National Nuclear Security Administration"},{"id":"https://openalex.org/G70659677","display_name":null,"funder_award_id":"89233218CNA000001","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7351994996","display_name":null,"funder_award_id":"DE-AC02-06CH11357","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7640496707","display_name":null,"funder_award_id":"75N91019D00024","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7806955302","display_name":null,"funder_award_id":"DE-AC52-07NA27344","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7954425250","display_name":null,"funder_award_id":"DE-AC02-06CH11357","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G7995982022","display_name":null,"funder_award_id":"DE-AC05","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8143874970","display_name":null,"funder_award_id":"AC02-06CH11357","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G8180170174","display_name":null,"funder_award_id":"DE-AC52-07NA27344","funder_id":"https://openalex.org/F4320332369","funder_display_name":"National Nuclear Security Administration"},{"id":"https://openalex.org/G8253304997","display_name":null,"funder_award_id":"17-SC-20-SC","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G8269158468","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G8374966015","display_name":null,"funder_award_id":"AC52-07NA27344","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8659807574","display_name":null,"funder_award_id":"89233218CNA000001","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8906985441","display_name":null,"funder_award_id":"00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G969889393","display_name":null,"funder_award_id":"DE-AC02-","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320332369","display_name":"National Nuclear Security Administration","ror":"https://ror.org/03sk1we31"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4381551344.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W1531601525","https://openalex.org/W2525546094","https://openalex.org/W1730977462","https://openalex.org/W97160839","https://openalex.org/W2914522629","https://openalex.org/W2339632025","https://openalex.org/W2892509520"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,23,93,165],"(RL)":[2],"has":[3,41],"made":[4],"significant":[5],"strides":[6],"in":[7,68,76,176],"various":[8],"complex":[9],"domains.":[10],"However,":[11],"identifying":[12],"an":[13,119],"effective":[14],"policy":[15,87,150,160],"via":[16,162],"RL":[17],"often":[18,40],"necessitates":[19],"extensive":[20],"exploration.":[21,35],"Imitation":[22],"aims":[24],"to":[25,33,43,73,107,124],"mitigate":[26],"this":[27],"issue":[28],"by":[29],"using":[30],"expert":[31],"demonstrations":[32],"guide":[34],"In":[36,98],"real-world":[37],"scenarios,":[38],"one":[39,128],"access":[42],"multiple":[44,95,167],"suboptimal":[45,96],"black-box":[46],"experts,":[47],"rather":[48],"than":[49],"a":[50,66,84,133,170],"single":[51],"optimal":[52],"oracle.":[53],"These":[54],"experts":[55],"do":[56],"not":[57],"universally":[58],"outperform":[59],"each":[60],"other":[61],"across":[62,169],"all":[63],"states,":[64],"presenting":[65],"challenge":[67],"actively":[69,101],"deciding":[70],"which":[71,77,103,126],"oracle":[72],"use":[74],"and":[75,82,109,115,137,141],"state.":[78],"We":[79,131],"introduce":[80],"MAPS":[81,100,140],"MAPS-SE,":[83],"class":[85],"of":[86,104,173],"improvement":[88,151],"algorithms":[89],"that":[90,139,156],"perform":[91],"imitation":[92,164],"from":[94,166],"oracles.":[97],"particular,":[99],"selects":[102],"the":[105,148,177],"oracles":[106,168],"imitate":[108],"improve":[110],"their":[111],"value":[112],"function":[113],"estimates,":[114],"MAPS-SE":[116,142,157],"additionally":[117],"leverages":[118],"active":[120],"state":[121],"exploration":[122],"criterion":[123],"determine":[125],"states":[127],"should":[129],"explore.":[130],"provide":[132],"comprehensive":[134],"theoretical":[135],"analysis":[136],"demonstrate":[138],"enjoy":[143],"sample":[144],"efficiency":[145],"advantage":[146],"over":[147],"state-of-the-art":[149],"algorithms.":[152],"Empirical":[153],"results":[154],"show":[155],"significantly":[158],"accelerates":[159],"optimization":[161],"state-wise":[163],"broad":[171],"spectrum":[172],"control":[174],"tasks":[175],"DeepMind":[178],"Control":[179],"Suite.":[180],"Our":[181],"code":[182],"is":[183],"publicly":[184],"available":[185],"at:":[186],"https://github.com/ripl/maps.":[187]},"counts_by_year":[],"updated_date":"2026-05-09T13:55:54.758798","created_date":"2025-10-10T00:00:00"}
