{"id":"https://openalex.org/W2783683035","doi":"https://doi.org/10.1109/cdc.2017.8263978","title":"Distributed lifelong reinforcement learning with sub-linear regret","display_name":"Distributed lifelong reinforcement learning with sub-linear regret","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2783683035","doi":"https://doi.org/10.1109/cdc.2017.8263978","mag":"2783683035"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2017.8263978","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2017.8263978","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE 56th Annual 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/A5000651751","display_name":"Rasul Tutunov","orcid":"https://orcid.org/0000-0002-6495-6437"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rasul Tutunov","raw_affiliation_strings":["PROWLER.io., Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PROWLER.io., Cambridge, UK","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044041959","display_name":"Julia El-Zini","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Julia El-Zini","raw_affiliation_strings":["PROWLER.io., American University of Beirut, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PROWLER.io., American University of Beirut, Cambridge, UK","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027297585","display_name":"Haitham Bou-Ammar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haitham Bou-Ammar","raw_affiliation_strings":["PROWLER.io., American University of Beirut, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PROWLER.io., American University of Beirut, Cambridge, UK","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078288116","display_name":"Ali Jadbabaie","orcid":"https://orcid.org/0000-0003-1122-3069"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ali Jadbabaie","raw_affiliation_strings":["Massachusetts Institute of Technology, Boston, US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Boston, US","institution_ids":["https://openalex.org/I63966007","https://openalex.org/I111088046"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8062,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.78577767,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"26","issue":null,"first_page":"2254","last_page":"2259"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9990000128746033,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/regret","display_name":"Regret","score":0.9507642388343811},{"id":"https://openalex.org/keywords/sublinear-function","display_name":"Sublinear function","score":0.9421858787536621},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8477693796157837},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6957461833953857},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6350557804107666},{"id":"https://openalex.org/keywords/lifelong-learning","display_name":"Lifelong learning","score":0.5841268301010132},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.42942237854003906},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3718271255493164},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3268301486968994},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3130533695220947},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18412810564041138},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.18217289447784424},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.12402057647705078},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08960011601448059}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.9507642388343811},{"id":"https://openalex.org/C117160843","wikidata":"https://www.wikidata.org/wiki/Q338652","display_name":"Sublinear function","level":2,"score":0.9421858787536621},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8477693796157837},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6957461833953857},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6350557804107666},{"id":"https://openalex.org/C108771440","wikidata":"https://www.wikidata.org/wiki/Q368475","display_name":"Lifelong learning","level":2,"score":0.5841268301010132},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.42942237854003906},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3718271255493164},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3268301486968994},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3130533695220947},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18412810564041138},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.18217289447784424},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.12402057647705078},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08960011601448059},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc.2017.8263978","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2017.8263978","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE 56th Annual Conference on Decision and Control (CDC)","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":29,"referenced_works":["https://openalex.org/W110451278","https://openalex.org/W914658793","https://openalex.org/W1515851193","https://openalex.org/W1519626139","https://openalex.org/W1626155273","https://openalex.org/W1701050018","https://openalex.org/W1984625914","https://openalex.org/W2012392077","https://openalex.org/W2044212084","https://openalex.org/W2046387702","https://openalex.org/W2097381042","https://openalex.org/W2106008664","https://openalex.org/W2107132870","https://openalex.org/W2110302464","https://openalex.org/W2125612430","https://openalex.org/W2129027292","https://openalex.org/W2154806059","https://openalex.org/W2159459871","https://openalex.org/W2164278908","https://openalex.org/W2169743339","https://openalex.org/W2296319761","https://openalex.org/W2963199297","https://openalex.org/W4250589301","https://openalex.org/W4294585425","https://openalex.org/W4297799385","https://openalex.org/W6631089601","https://openalex.org/W6674600207","https://openalex.org/W6676004469","https://openalex.org/W6676172054"],"related_works":["https://openalex.org/W2971351794","https://openalex.org/W4376155396","https://openalex.org/W1947085858","https://openalex.org/W2174986909","https://openalex.org/W2527791220","https://openalex.org/W2101991911","https://openalex.org/W2155070487","https://openalex.org/W4311589891","https://openalex.org/W1925875298","https://openalex.org/W4292701710"],"abstract_inverted_index":{"In":[0],"this":[1,45,63],"paper":[2],"we":[3],"propose":[4],"a":[5,16],"distributed":[6],"second-order":[7],"method":[8,47],"for":[9,50],"lifelong":[10],"reinforcement":[11],"learning":[12],"(LRL).":[13],"Upon":[14],"observing":[15],"new":[17,46],"task,":[18],"our":[19,58],"algorithm":[20],"scales":[21],"state-of-the-art":[22],"LRL":[23],"by":[24],"approximating":[25],"the":[26,41,51,55],"Newton":[27],"direction":[28],"up-to-any":[29],"arbitrary":[30],"precision":[31],"\u03f5":[32],">":[33],"0,":[34],"while":[35],"guaranteeing":[36],"accurate":[37],"solutions.":[38],"We":[39],"analyze":[40],"theoretical":[42],"properties":[43],"of":[44,57],"and":[48],"derive,":[49],"first":[52],"time":[53],"to":[54],"best":[56],"knowledge,":[59],"sublinear":[60],"regret":[61],"under":[62],"setting.":[64]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}