{"id":"https://openalex.org/W2491319378","doi":"https://doi.org/10.1109/cdc.2016.7798399","title":"An exact distributed newton method for reinforcement learning","display_name":"An exact distributed newton method for reinforcement learning","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2491319378","doi":"https://doi.org/10.1109/cdc.2016.7798399","mag":"2491319378"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2016.7798399","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2016.7798399","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 55th 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/1608.00070","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000651751","display_name":"Rasul Tutunov","orcid":"https://orcid.org/0000-0002-6495-6437"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rasul Tutunov","raw_affiliation_strings":["Department of Computer and Information Science, University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science, University of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027297585","display_name":"Haitham Bou-Ammar","orcid":null},"institutions":[{"id":"https://openalex.org/I98635879","display_name":"American University of Beirut","ror":"https://ror.org/04pznsd21","country_code":"LB","type":"education","lineage":["https://openalex.org/I98635879"]}],"countries":["LB"],"is_corresponding":false,"raw_author_name":"Haitham Bou Ammar","raw_affiliation_strings":["Department of Computer Science & American University of Beirut, Lebanon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science & American University of Beirut, Lebanon","institution_ids":["https://openalex.org/I98635879"]}]},{"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/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ali Jadbabaie","raw_affiliation_strings":["Department of Computer and Information Science, University of Pennsylvania, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science, University of Pennsylvania, USA","institution_ids":["https://openalex.org/I79576946"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4416,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.78994413,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"3","issue":null,"first_page":"1003","last_page":"1008"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987000226974487,"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":0.9987000226974487,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9927999973297119,"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"}},{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9905999898910522,"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":0.8723093271255493},{"id":"https://openalex.org/keywords/hessian-matrix","display_name":"Hessian matrix","score":0.7921894788742065},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7425347566604614},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.688567578792572},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.623939573764801},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6063982844352722},{"id":"https://openalex.org/keywords/newtons-method","display_name":"Newton's method","score":0.6038820743560791},{"id":"https://openalex.org/keywords/diagonal","display_name":"Diagonal","score":0.5665563344955444},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.506112277507782},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.4872678518295288},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4808536171913147},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.4054804742336273},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3456370234489441},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.34039419889450073},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3364419639110565},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.1979503035545349},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.06563800573348999}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8723093271255493},{"id":"https://openalex.org/C203616005","wikidata":"https://www.wikidata.org/wiki/Q620495","display_name":"Hessian matrix","level":2,"score":0.7921894788742065},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7425347566604614},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.688567578792572},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.623939573764801},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6063982844352722},{"id":"https://openalex.org/C85189116","wikidata":"https://www.wikidata.org/wiki/Q374195","display_name":"Newton's method","level":3,"score":0.6038820743560791},{"id":"https://openalex.org/C130367717","wikidata":"https://www.wikidata.org/wiki/Q189791","display_name":"Diagonal","level":2,"score":0.5665563344955444},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.506112277507782},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.4872678518295288},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4808536171913147},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.4054804742336273},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3456370234489441},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34039419889450073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3364419639110565},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.1979503035545349},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.06563800573348999},{"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/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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":4,"locations":[{"id":"doi:10.1109/cdc.2016.7798399","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2016.7798399","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 55th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1608.00070","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1608.00070","pdf_url":"https://arxiv.org/pdf/1608.00070","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:2491319378","is_oa":true,"landing_page_url":"http://arxiv.org/pdf/1608.00070.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":"doi:10.48550/arxiv.1608.00070","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1608.00070","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:1608.00070","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1608.00070","pdf_url":"https://arxiv.org/pdf/1608.00070","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1533535072","https://openalex.org/W1701050018","https://openalex.org/W1848094219","https://openalex.org/W1896212383","https://openalex.org/W2008164266","https://openalex.org/W2010315937","https://openalex.org/W2012392077","https://openalex.org/W2026198955","https://openalex.org/W2044212084","https://openalex.org/W2046387702","https://openalex.org/W2110302464","https://openalex.org/W2119007372","https://openalex.org/W2119717200","https://openalex.org/W2129027292","https://openalex.org/W2148087609","https://openalex.org/W2155027007","https://openalex.org/W2164278908","https://openalex.org/W2235081654","https://openalex.org/W2296319761","https://openalex.org/W2962748029","https://openalex.org/W3145803272","https://openalex.org/W4250589301","https://openalex.org/W6624272836","https://openalex.org/W6631863446","https://openalex.org/W6639571173","https://openalex.org/W6683204974","https://openalex.org/W6687775544","https://openalex.org/W6689645015"],"related_works":["https://openalex.org/W3130457203","https://openalex.org/W2996995192","https://openalex.org/W2971494186","https://openalex.org/W3188189585","https://openalex.org/W2158504546","https://openalex.org/W2151568021","https://openalex.org/W2113455337","https://openalex.org/W3186021868","https://openalex.org/W2278682511","https://openalex.org/W2921375133","https://openalex.org/W2954160693","https://openalex.org/W2883309838","https://openalex.org/W2164535072","https://openalex.org/W2609423269","https://openalex.org/W2794792943","https://openalex.org/W2789587413","https://openalex.org/W2999664547","https://openalex.org/W2158738729","https://openalex.org/W2803889156","https://openalex.org/W3185667776"],"abstract_inverted_index":{"In":[0],"this":[1,32,102],"paper,":[2],"we":[3,77,97],"propose":[4],"a":[5,55,90,106],"distributed":[6],"second-order":[7],"method":[8,104],"for":[9],"reinforcement":[10,110],"learning.":[11],"Our":[12],"approach":[13],"is":[14],"the":[15,35,39,44,48,66,74,93,99],"fastest":[16],"in":[17],"literature":[18],"so-far":[19],"as":[20],"it":[21],"outperforms":[22],"state-of-the-art":[23],"methods,":[24],"including":[25],"ADMM,":[26],"by":[27,33],"significant":[28],"margins.":[29],"We":[30,64],"achieve":[31],"exploiting":[34],"sparsity":[36],"pattern":[37],"of":[38,46,53,57,62,92,101,108],"dual":[40],"Hessian":[41],"and":[42,71],"transforming":[43],"problem":[45],"computing":[47],"Newton":[49],"direction":[50],"to":[51,81],"one":[52],"solving":[54],"sequence":[56],"symmetric":[58],"diagonally":[59],"dominant":[60],"system":[61],"equations.":[63],"validate":[65],"above":[67],"claim":[68],"both":[69],"theoretically":[70],"empirically.":[72],"On":[73],"theoretical":[75],"side,":[76],"prove":[78],"that":[79],"similar":[80],"exact":[82],"Newton,":[83],"our":[84],"algorithm":[85],"exhibits":[86],"super-linear":[87],"convergence":[88],"within":[89],"neighborhood":[91],"optimal":[94],"solution.":[95],"Empirically,":[96],"demonstrate":[98],"superiority":[100],"new":[103],"on":[105],"set":[107],"benchmark":[109],"learning":[111],"tasks.":[112]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}