{"id":"https://openalex.org/W2964061343","doi":"https://doi.org/10.1609/aaai.v32i1.11687","title":"Alternating Optimisation and Quadrature for Robust Control","display_name":"Alternating Optimisation and Quadrature for Robust Control","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2964061343","doi":"https://doi.org/10.1609/aaai.v32i1.11687","mag":"2964061343"},"language":"en","primary_location":{"id":"pmh:oai:ojs.aaai.org:article/11687","doi":"https://doi.org/10.1609/aaai.v32i1.11687","is_oa":true,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/11687","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/11687/11546","source":{"id":"https://openalex.org/S4306400155","display_name":"AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801652627","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/I2801652627"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/11687/11546","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030103572","display_name":"Supratik Paul","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Paul, Supratik","raw_affiliation_strings":["University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048630321","display_name":"Konstantinos I. Chatzilygeroudis","orcid":"https://orcid.org/0000-0003-3585-1027","observed_orcids":["https://orcid.org/0000-0003-3585-1027"]},"institutions":[{"id":"https://openalex.org/I4210127166","display_name":"Centre Inria de l'Universit\u00e9 de Lorraine","ror":"https://ror.org/03fcjvn64","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210127166"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Chatzilygeroudis, Konstantinos","raw_affiliation_strings":["Inria, Villers-l\u00e8s-Nancy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria, Villers-l\u00e8s-Nancy","institution_ids":["https://openalex.org/I4210127166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043239539","display_name":"Kamil Ciosek","orcid":"https://orcid.org/0000-0002-0238-9393","observed_orcids":["https://orcid.org/0000-0002-0238-9393"]},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ciosek, Kamil","raw_affiliation_strings":["University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032227198","display_name":"Jean-Baptiste Mouret","orcid":"https://orcid.org/0000-0002-2513-027X","observed_orcids":["https://orcid.org/0000-0002-2513-027X"]},"institutions":[{"id":"https://openalex.org/I4210127166","display_name":"Centre Inria de l'Universit\u00e9 de Lorraine","ror":"https://ror.org/03fcjvn64","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210127166"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mouret, Jean-Baptiste","raw_affiliation_strings":["Inria, Villers-l\u00e8s-Nancy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria, Villers-l\u00e8s-Nancy","institution_ids":["https://openalex.org/I4210127166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002007044","display_name":"Michael A. Osborne","orcid":"https://orcid.org/0000-0003-1959-012X","observed_orcids":["https://orcid.org/0000-0003-1959-012X"]},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Osborne, Michael","raw_affiliation_strings":["University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056879203","display_name":"Shimon Whiteson","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Whiteson, Shimon","raw_affiliation_strings":["University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4436,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.84575524,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":98},"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":0.9115999937057495,"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":0.9115999937057495,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.08160000294446945,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0010000000474974513,"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/robust-control","display_name":"robust control","score":0.7749999761581421},{"id":"https://openalex.org/keywords/bayesian-optimization","display_name":"Bayesian optimization","score":0.8519999980926514},{"id":"https://openalex.org/keywords/bayesian-quadrature","display_name":"Bayesian quadrature","score":0.9990000128746033},{"id":"https://openalex.org/keywords/rare-events","display_name":"rare events","score":0.6430000066757202},{"id":"https://openalex.org/keywords/environment-variables","display_name":"environment variables","score":0.5519999861717224},{"id":"https://openalex.org/keywords/simulator-based-learning","display_name":"simulator-based learning","score":0.593999981880188},{"id":"https://openalex.org/keywords/optimal-policy-learning","display_name":"optimal policy learning","score":0.6320000290870667}],"concepts":[{"id":"https://openalex.org/C2780695315","wikidata":"https://www.wikidata.org/wiki/Q3799040","display_name":"Unobservable","level":2,"score":0.9342679977416992},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.702454686164856},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.682172954082489},{"id":"https://openalex.org/C62869609","wikidata":"https://www.wikidata.org/wiki/Q28137","display_name":"Quadrature (astronomy)","level":2,"score":0.6655481457710266},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6392686367034912},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5201942920684814},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.45066511631011963},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.4136057496070862},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3574981093406677},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3571656346321106},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2458653748035431},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.22762876749038696},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18543413281440735},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:ojs.aaai.org:article/11687","doi":"https://doi.org/10.1609/aaai.v32i1.11687","is_oa":true,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/11687","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/11687/11546","source":{"id":"https://openalex.org/S4306400155","display_name":"AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801652627","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/I2801652627"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:ora.ox.ac.uk:uuid:abd7c997-b0fb-4e66-b601-f82184500cbf","doi":null,"is_oa":true,"landing_page_url":"https://ora.ox.ac.uk/objects/uuid:abd7c997-b0fb-4e66-b601-f82184500cbf","pdf_url":"https://ora.ox.ac.uk/objects/uuid:abd7c997-b0fb-4e66-b601-f82184500cbf","source":{"id":"https://openalex.org/S4306402636","display_name":"Oxford University Research Archive (ORA) (University of Oxford)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I40120149","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/I40120149"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symplectic Elements at Oxford","raw_type":"http://purl.org/coar/resource_type/c_5794"}],"best_oa_location":{"id":"pmh:oai:ojs.aaai.org:article/11687","doi":"https://doi.org/10.1609/aaai.v32i1.11687","is_oa":true,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/11687","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/11687/11546","source":{"id":"https://openalex.org/S4306400155","display_name":"AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801652627","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/I2801652627"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G6666270918","display_name":null,"funder_award_id":"637972","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2964061343.pdf","grobid_xml":"https://content.openalex.org/works/W2964061343.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W190473450","https://openalex.org/W770013183","https://openalex.org/W1483202606","https://openalex.org/W1529817821","https://openalex.org/W1533803232","https://openalex.org/W1738827650","https://openalex.org/W1746819321","https://openalex.org/W1771410628","https://openalex.org/W2018705428","https://openalex.org/W2096649264","https://openalex.org/W2098152875","https://openalex.org/W2099201756","https://openalex.org/W2100614560","https://openalex.org/W2110720940","https://openalex.org/W2111241577","https://openalex.org/W2117643431","https://openalex.org/W2121658992","https://openalex.org/W2126272934","https://openalex.org/W2131627640","https://openalex.org/W2140135625","https://openalex.org/W2158229980","https://openalex.org/W2325958504","https://openalex.org/W2529477964","https://openalex.org/W2565313327","https://openalex.org/W2602963933","https://openalex.org/W2767409068","https://openalex.org/W2903158431","https://openalex.org/W2962820140","https://openalex.org/W3124229194","https://openalex.org/W4230563027"],"related_works":["https://openalex.org/W2405358767","https://openalex.org/W3086586587","https://openalex.org/W2804860445","https://openalex.org/W6931708005","https://openalex.org/W2592857946","https://openalex.org/W2889893435","https://openalex.org/W3129243175","https://openalex.org/W2565313327","https://openalex.org/W2948316777","https://openalex.org/W4406612581"],"abstract_inverted_index":{"Bayesian":[0,85,88],"optimisation":[1,86],"has":[2],"been":[3],"successfully":[4],"applied":[5],"to":[6,28,90,97],"a":[7,48,55,64,114],"variety":[8],"of":[9,62,73,100],"reinforcement":[10],"learning":[11,18,30],"problems.":[12],"However,":[13],"the":[14,26,45,60,71,98,119],"traditional":[15],"approach":[16],"for":[17],"optimal":[19,120],"policies":[20],"in":[21,47,54,117],"simulators":[22],"does":[23],"not":[24,106],"utilise":[25],"opportunity":[27],"improve":[29],"by":[31,44],"adjusting":[32],"certain":[33],"environment":[34,46,74],"variables:":[35],"state":[36],"features":[37],"that":[38,128],"are":[39,52],"unobservable":[40],"and":[41,80,87,134],"randomly":[42],"determined":[43],"physical":[49],"setting":[50],"but":[51,112],"controllable":[53],"simulator.":[56],"This":[57],"paper":[58],"considers":[59],"problem":[61],"finding":[63],"robust":[65,96],"policy":[66],"while":[67],"taking":[68],"into":[69],"account":[70],"impact":[72],"variables.":[75],"We":[76],"present":[77],"Alternating":[78],"Optimisation":[79],"Quadrature":[81],"(ALOQ),":[82],"which":[83,104],"uses":[84],"quadrature":[89],"address":[91],"such":[92],"settings.":[93],"ALOQ":[94,129],"is":[95],"presence":[99],"significant":[101],"rare":[102],"events,":[103],"may":[105],"be":[107],"observable":[108],"under":[109],"random":[110],"sampling,":[111],"play":[113],"substantial":[115],"role":[116],"determining":[118],"policy.":[121],"Experimental":[122],"results":[123],"across":[124],"different":[125],"domains":[126],"show":[127],"can":[130],"learn":[131],"more":[132],"efficiently":[133],"robustly":[135],"than":[136],"existing":[137],"methods.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":4}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2019-07-30T00:00:00"}
