{"id":"https://openalex.org/W2913300107","doi":"https://doi.org/10.1109/allerton.2018.8636072","title":"Data Efficient Learning of Robust Control Policies","display_name":"Data Efficient Learning of Robust Control Policies","publication_year":2018,"publication_date":"2018-10-01","ids":{"openalex":"https://openalex.org/W2913300107","doi":"https://doi.org/10.1109/allerton.2018.8636072","mag":"2913300107"},"language":"en","primary_location":{"id":"doi:10.1109/allerton.2018.8636072","is_oa":false,"landing_page_url":"https://doi.org/10.1109/allerton.2018.8636072","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 56th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","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/A5035902535","display_name":"Susmit Jha","orcid":"https://orcid.org/0000-0001-5983-9095"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Susmit Jha","raw_affiliation_strings":["SRI International, Menlo Park, CA, US"],"affiliations":[{"raw_affiliation_string":"SRI International, Menlo Park, CA, US","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003908930","display_name":"Patrick Lincoln","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]},{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Patrick Lincoln","raw_affiliation_strings":["SRI International, Menlo Park, CA, US"],"affiliations":[{"raw_affiliation_string":"SRI International, Menlo Park, CA, US","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5035902535"],"corresponding_institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"],"apc_list":null,"apc_paid":null,"fwci":0.1629,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.61718821,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"518","issue":null,"first_page":"856","last_page":"861"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9965000152587891,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9965000152587891,"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":0.9948999881744385,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9923999905586243,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8284380435943604},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.6343449354171753},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.601736843585968},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5307471752166748},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5190618634223938},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5140865445137024},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5095610618591309},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.4990077018737793},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4509744346141815},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4470481872558594},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44459444284439087},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.41645359992980957},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.364546000957489},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3599666357040405},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18329933285713196}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8284380435943604},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.6343449354171753},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.601736843585968},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5307471752166748},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5190618634223938},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5140865445137024},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5095610618591309},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.4990077018737793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4509744346141815},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4470481872558594},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44459444284439087},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.41645359992980957},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.364546000957489},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3599666357040405},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18329933285713196},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/allerton.2018.8636072","is_oa":false,"landing_page_url":"https://doi.org/10.1109/allerton.2018.8636072","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 56th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1490488263","https://openalex.org/W1502922572","https://openalex.org/W1520597402","https://openalex.org/W1757796397","https://openalex.org/W1771410628","https://openalex.org/W2121863487","https://openalex.org/W2132602063","https://openalex.org/W2144174236","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2173248099","https://openalex.org/W2179284380","https://openalex.org/W2181623680","https://openalex.org/W2257979135","https://openalex.org/W2530944449","https://openalex.org/W2604883922","https://openalex.org/W2771827793","https://openalex.org/W2801572960","https://openalex.org/W2950471160","https://openalex.org/W2952629144","https://openalex.org/W2963149945","https://openalex.org/W2963864421","https://openalex.org/W2964112890","https://openalex.org/W4211049957","https://openalex.org/W4214717370","https://openalex.org/W4298857966","https://openalex.org/W6629804754","https://openalex.org/W6637967152","https://openalex.org/W6638018090","https://openalex.org/W6684921986","https://openalex.org/W6686008357","https://openalex.org/W6696324988","https://openalex.org/W6720501231","https://openalex.org/W6728367041","https://openalex.org/W6728925229","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W1964286703","https://openalex.org/W2169866437"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"data-efficient":[3],"methods":[4,50],"for":[5],"learning":[6,11,46,77,130],"robust":[7],"control":[8,20,49,79],"policies.":[9,80],"Reinforcement":[10],"has":[12],"emerged":[13],"as":[14,150,152],"an":[15,147,153],"effective":[16],"approach":[17,65,83,144],"to":[18,37,39,74,107,146,163],"learn":[19],"policies":[21],"by":[22],"interacting":[23],"directly":[24],"with":[25,47],"the":[26,40,68,76,96,109,117,120,132,140,170,176,185],"plant,":[27],"but":[28],"it":[29],"requires":[30],"a":[31,63,92,103,112,125,191],"significant":[32],"number":[33,177],"of":[34,70,78,85,111,119,172,178,187,193],"example":[35],"trajectories":[36],"converge":[38],"optimal":[41,148],"policy.":[42],"Combining":[43],"model-free":[44],"reinforcement":[45,129],"model-based":[48],"achieves":[51],"better":[52],"data-efficiency":[53],"via":[54],"simultaneous":[55],"system":[56],"identification":[57],"and":[58,99,123,169],"controller":[59],"synthesis.":[60],"We":[61,183],"study":[62],"novel":[64],"that":[66,136],"exploits":[67],"existence":[69],"approximate":[71,154],"physics":[72,114,134,155],"models":[73],"accelerate":[75],"The":[81,143,157],"proposed":[82],"consists":[84],"iterating":[86],"through":[87],"three":[88],"key":[89],"steps:":[90],"evaluating":[91,164],"selected":[93,121],"policy":[94,127,149],"on":[95,131,190],"real-world":[97],"plant":[98],"recording":[100],"trajectories,":[101],"building":[102],"Gaussian":[104,173],"process":[105],"model":[106,115,135],"predict":[108],"reality-gap":[110],"parametric":[113],"in":[116],"neighborhood":[118],"policy,":[122],"synthesizing":[124],"new":[126],"using":[128,196],"refined":[133],"most":[137],"likely":[138],"approximates":[139],"real":[141,158,180],"plant.":[142],"converges":[145],"well":[151],"model.":[156],"world":[159,181],"experiments":[160],"are":[161],"limited":[162],"only":[165],"promising":[166],"candidate":[167],"policies,":[168],"use":[171],"processes":[174],"minimizes":[175],"required":[179],"trajectories.":[182],"demonstrate":[184],"effectiveness":[186],"our":[188],"techniques":[189],"set":[192],"simulation":[194],"case-studies":[195],"OpenAI":[197],"gym":[198],"environments.":[199]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}