{"id":"https://openalex.org/W4315488719","doi":"https://doi.org/10.1109/cdc51059.2022.9993035","title":"Newton-based Policy Search for Networked Multi-agent Reinforcement Learning","display_name":"Newton-based Policy Search for Networked Multi-agent Reinforcement Learning","publication_year":2022,"publication_date":"2022-12-06","ids":{"openalex":"https://openalex.org/W4315488719","doi":"https://doi.org/10.1109/cdc51059.2022.9993035"},"language":"en","primary_location":{"id":"doi:10.1109/cdc51059.2022.9993035","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cdc51059.2022.9993035","pdf_url":null,"source":{"id":"https://openalex.org/S4363607710","display_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5035756421","display_name":"Giorgio Manganini","orcid":"https://orcid.org/0000-0002-5394-4094"},"institutions":[{"id":"https://openalex.org/I4210150763","display_name":"Gran Sasso Science Institute","ror":"https://ror.org/043qcb444","country_code":"IT","type":"education","lineage":["https://openalex.org/I160013858","https://openalex.org/I4210150763"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giorgio Manganini","raw_affiliation_strings":["Gran Sasso Science Institute (GSSI),Department of Computer Science,L’Aquila,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gran Sasso Science Institute (GSSI),Department of Computer Science,L’Aquila,Italy","institution_ids":["https://openalex.org/I4210150763"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066302008","display_name":"Simone Fioravanti","orcid":"https://orcid.org/0000-0002-3850-0786"},"institutions":[{"id":"https://openalex.org/I4210150763","display_name":"Gran Sasso Science Institute","ror":"https://ror.org/043qcb444","country_code":"IT","type":"education","lineage":["https://openalex.org/I160013858","https://openalex.org/I4210150763"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Simone Fioravanti","raw_affiliation_strings":["Gran Sasso Science Institute (GSSI),Department of Computer Science,L’Aquila,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gran Sasso Science Institute (GSSI),Department of Computer Science,L’Aquila,Italy","institution_ids":["https://openalex.org/I4210150763"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048076721","display_name":"Giorgia Ramponi","orcid":"https://orcid.org/0000-0002-3076-5448"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Giorgia Ramponi","raw_affiliation_strings":["ETH AI Center,Zürich,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH AI Center,Zürich,Switzerland","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21519633,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"17","issue":null,"first_page":"7241","last_page":"7247"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9991000294685364,"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"}},"topics":[{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9991000294685364,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980000257492065,"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/T10621","display_name":"Gene Regulatory Network Analysis","score":0.9799000024795532,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8197720646858215},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.7231496572494507},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6496732234954834},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6159560680389404},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.582512378692627},{"id":"https://openalex.org/keywords/newtons-method","display_name":"Newton's method","score":0.564625084400177},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5364782214164734},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5024559497833252},{"id":"https://openalex.org/keywords/local-convergence","display_name":"Local convergence","score":0.4474678337574005},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.44001826643943787},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.4317629337310791},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.41114991903305054},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.32659226655960083},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.2822903096675873},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2802324593067169},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.25919780135154724},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17123720049858093},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.10713532567024231},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.08611825108528137}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8197720646858215},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7231496572494507},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6496732234954834},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6159560680389404},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.582512378692627},{"id":"https://openalex.org/C85189116","wikidata":"https://www.wikidata.org/wiki/Q374195","display_name":"Newton's method","level":3,"score":0.564625084400177},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5364782214164734},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5024559497833252},{"id":"https://openalex.org/C117898588","wikidata":"https://www.wikidata.org/wiki/Q6664310","display_name":"Local convergence","level":3,"score":0.4474678337574005},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.44001826643943787},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.4317629337310791},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.41114991903305054},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.32659226655960083},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.2822903096675873},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2802324593067169},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25919780135154724},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17123720049858093},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.10713532567024231},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.08611825108528137},{"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc51059.2022.9993035","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cdc51059.2022.9993035","pdf_url":null,"source":{"id":"https://openalex.org/S4363607710","display_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Partnerships for the goals","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W583627169","https://openalex.org/W594357522","https://openalex.org/W1542343170","https://openalex.org/W2099618002","https://openalex.org/W2119717200","https://openalex.org/W2125612430","https://openalex.org/W2144446635","https://openalex.org/W2156737235","https://openalex.org/W2167117957","https://openalex.org/W2257979135","https://openalex.org/W2294586855","https://openalex.org/W2565081646","https://openalex.org/W2602024037","https://openalex.org/W2695227890","https://openalex.org/W2807424650","https://openalex.org/W2811008754","https://openalex.org/W2913326990","https://openalex.org/W2962851675","https://openalex.org/W2964005211","https://openalex.org/W2973229164","https://openalex.org/W2991046523","https://openalex.org/W3006882295","https://openalex.org/W3010758700","https://openalex.org/W3023368031","https://openalex.org/W3105688066","https://openalex.org/W3106753174","https://openalex.org/W3153787838","https://openalex.org/W3176552354","https://openalex.org/W4251986490","https://openalex.org/W4301014524","https://openalex.org/W4301501993","https://openalex.org/W4306179383","https://openalex.org/W4381327650","https://openalex.org/W6600828528","https://openalex.org/W6683195989","https://openalex.org/W6728155968","https://openalex.org/W6730905388","https://openalex.org/W6738796088","https://openalex.org/W6739717732","https://openalex.org/W6749032143","https://openalex.org/W6751921135","https://openalex.org/W6846392434"],"related_works":["https://openalex.org/W2387535608","https://openalex.org/W2350788688","https://openalex.org/W2799975713","https://openalex.org/W2380062341","https://openalex.org/W2367976695","https://openalex.org/W2762113365","https://openalex.org/W4297921956","https://openalex.org/W2951861326","https://openalex.org/W4308500253","https://openalex.org/W1985487460"],"abstract_inverted_index":{"Newton\u2019s":[0,37,110],"method":[1,38],"is":[2,39,134],"a":[3,9,55,65,122,200],"standard":[4],"optimization":[5,44],"algorithm,":[6,93],"characterized":[7],"by":[8,105,125],"fast":[10],"rate":[11,33],"of":[12,100,127,143,154,188],"convergence":[13,32,171,195],"and":[14,34,117,137,151,157,191],"used":[15,41],"in":[16,45,64,121],"many":[17],"popular":[18],"approximated":[19,109],"methods":[20],"that":[21],"use":[22],"second-order":[23],"information.":[24],"Despite":[25],"its":[26,193],"well":[27],"understood":[28],"theoretical":[29,152,179],"properties,":[30,180],"quadratic":[31],"extended":[35],"applications,":[36],"seldom":[40],"for":[42,60,83,97,112],"policy":[43,62,104],"Multi-Agent":[46],"Reinforcement":[47],"Learning":[48],"problems.":[49],"In":[50,90],"this":[51],"work":[52],"we":[53,169,181],"investigate":[54],"distributed":[56,123,203],"Newton":[57],"consensus":[58,130],"scheme":[59],"performing":[61],"search":[63],"networked":[66],"cooperative":[67],"environment,":[68],"where":[69],"the":[70,85,91,94,98,101,113,144,149,155,165,178,186,189],"agents":[71,95],"are":[72],"endowed":[73],"with":[74],"private":[75],"local":[76],"rewards,":[77],"though":[78],"they":[79],"aim":[80],"to":[81,164,199],"collaborate":[82],"maximizing":[84],"network-wise":[86],"averaged":[87],"long-term":[88],"return.":[89],"proposed":[92],"seek":[96],"parameters":[99],"optimal":[102],"global":[103,114,145,162],"locally":[106],"computing":[107],"an":[108,128],"direction":[111],"objective":[115],"function,":[116],"sequentially":[118],"update":[119],"it":[120],"fashion":[124],"means":[126],"average":[129],"procedure.":[131],"The":[132],"strategy":[133],"purely":[135],"policy-based":[136],"does":[138],"not":[139],"involve":[140],"any":[141],"representation":[142],"value-function.":[146],"We":[147],"analyse":[148],"computational":[150],"properties":[153],"algorithm":[156],"prove,":[158],"under":[159,174],"suitable":[160],"assumptions,":[161],"converge":[163],"true":[166],"maximizer.":[167],"Additionally,":[168],"provide":[170],"guarantees":[172],"also":[173],"finite-sample":[175],"conditions.":[176],"Beside":[177],"perform":[182],"numerical":[183],"experiments":[184],"showing":[185],"validity":[187],"approach":[190],"highlight":[192],"improved":[194],"speed":[196],"when":[197],"compared":[198],"simpler":[201],"first-order":[202],"method.":[204]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}