{"id":"https://openalex.org/W3198538443","doi":"https://doi.org/10.1007/s13235-022-00449-9","title":"Multi-Agent Natural Actor-Critic Reinforcement Learning Algorithms","display_name":"Multi-Agent Natural Actor-Critic Reinforcement Learning Algorithms","publication_year":2022,"publication_date":"2022-06-16","ids":{"openalex":"https://openalex.org/W3198538443","doi":"https://doi.org/10.1007/s13235-022-00449-9","mag":"3198538443"},"language":"en","primary_location":{"id":"doi:10.1007/s13235-022-00449-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s13235-022-00449-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s13235-022-00449-9.pdf","source":{"id":"https://openalex.org/S2502731256","display_name":"Dynamic Games and Applications","issn_l":"2153-0785","issn":["2153-0785","2153-0793"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320186","host_organization_name":"Birkh\u00e4user","host_organization_lineage":["https://openalex.org/P4310320186","https://openalex.org/P4310319900"],"host_organization_lineage_names":["Birkh\u00e4user","Springer Science+Business Media"],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Dynamic Games and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s13235-022-00449-9.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069928361","display_name":"Prashant Trivedi","orcid":"https://orcid.org/0000-0002-7709-1452"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Prashant Trivedi","raw_affiliation_strings":["Industrial Engineering and Operations Research IIT Bombay, Mumbai, India"],"raw_orcid":"https://orcid.org/0000-0002-7709-1452","affiliations":[{"raw_affiliation_string":"Industrial Engineering and Operations Research IIT Bombay, Mumbai, India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084320426","display_name":"N. Hemachandra","orcid":"https://orcid.org/0000-0003-2917-1551"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Nandyala Hemachandra","raw_affiliation_strings":["Industrial Engineering and Operations Research IIT Bombay, Mumbai, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Industrial Engineering and Operations Research IIT Bombay, Mumbai, India","institution_ids":["https://openalex.org/I162827531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5069928361"],"corresponding_institution_ids":["https://openalex.org/I162827531"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":0.4273,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.61285198,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9979000091552734,"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":0.9979000091552734,"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":0.9943000078201294,"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/T10917","display_name":"Smart Grid Security and Resilience","score":0.9927999973297119,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7951414585113525},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6598038673400879},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5290122628211975},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4907885491847992},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4363614320755005},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4315584599971771},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.41499608755111694},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.39743608236312866},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25983428955078125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23934191465377808}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7951414585113525},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6598038673400879},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5290122628211975},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4907885491847992},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4363614320755005},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4315584599971771},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.41499608755111694},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.39743608236312866},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25983428955078125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23934191465377808},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s13235-022-00449-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s13235-022-00449-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s13235-022-00449-9.pdf","source":{"id":"https://openalex.org/S2502731256","display_name":"Dynamic Games and Applications","issn_l":"2153-0785","issn":["2153-0785","2153-0793"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320186","host_organization_name":"Birkh\u00e4user","host_organization_lineage":["https://openalex.org/P4310320186","https://openalex.org/P4310319900"],"host_organization_lineage_names":["Birkh\u00e4user","Springer Science+Business Media"],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Dynamic Games and Applications","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:spr:dyngam:v:13:y:2023:i:1:d:10.1007_s13235-022-00449-9","is_oa":false,"landing_page_url":"http://link.springer.com/10.1007/s13235-022-00449-9","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s13235-022-00449-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s13235-022-00449-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s13235-022-00449-9.pdf","source":{"id":"https://openalex.org/S2502731256","display_name":"Dynamic Games and Applications","issn_l":"2153-0785","issn":["2153-0785","2153-0793"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320186","host_organization_name":"Birkh\u00e4user","host_organization_lineage":["https://openalex.org/P4310320186","https://openalex.org/P4310319900"],"host_organization_lineage_names":["Birkh\u00e4user","Springer Science+Business Media"],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Dynamic Games and Applications","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6399999856948853,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320323448","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3198538443.pdf","grobid_xml":"https://content.openalex.org/works/W3198538443.grobid-xml"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W1499021337","https://openalex.org/W1518858799","https://openalex.org/W1534630452","https://openalex.org/W1564755532","https://openalex.org/W1582706191","https://openalex.org/W1594783240","https://openalex.org/W1869778509","https://openalex.org/W1970789124","https://openalex.org/W1979043738","https://openalex.org/W2007854530","https://openalex.org/W2011393317","https://openalex.org/W2044212084","https://openalex.org/W2046376809","https://openalex.org/W2052387029","https://openalex.org/W2052390455","https://openalex.org/W2071983464","https://openalex.org/W2078394884","https://openalex.org/W2094387729","https://openalex.org/W2098432798","https://openalex.org/W2098863504","https://openalex.org/W2099618002","https://openalex.org/W2101915445","https://openalex.org/W2117905067","https://openalex.org/W2119567691","https://openalex.org/W2121703796","https://openalex.org/W2121863487","https://openalex.org/W2146890818","https://openalex.org/W2155027007","https://openalex.org/W2156737235","https://openalex.org/W2157701998","https://openalex.org/W2172968643","https://openalex.org/W2235056388","https://openalex.org/W2913326990","https://openalex.org/W2963433607","https://openalex.org/W2963649943","https://openalex.org/W2963747324","https://openalex.org/W2964258803","https://openalex.org/W2991046523","https://openalex.org/W2997604484","https://openalex.org/W3034426742","https://openalex.org/W3086499488","https://openalex.org/W3092703335","https://openalex.org/W3104243370","https://openalex.org/W3132503596","https://openalex.org/W3153787838","https://openalex.org/W3171210634","https://openalex.org/W3176552354","https://openalex.org/W3210565380","https://openalex.org/W4214717370","https://openalex.org/W4229706427","https://openalex.org/W4251710608","https://openalex.org/W4252158954","https://openalex.org/W4301014524","https://openalex.org/W4391410851","https://openalex.org/W6777371779"],"related_works":["https://openalex.org/W1517908938","https://openalex.org/W2165272709","https://openalex.org/W1999937375","https://openalex.org/W2375053028","https://openalex.org/W1981749300","https://openalex.org/W2373502461","https://openalex.org/W2386410636","https://openalex.org/W586558997","https://openalex.org/W3123775475","https://openalex.org/W2295113609"],"abstract_inverted_index":{"Abstract":[0],"Multi-agent":[1],"actor-critic":[2,21,162],"algorithms":[3,23,76,242],"are":[4],"an":[5,203],"important":[6],"part":[7],"of":[8,42,48,71,83,103,120,130,144,148,157,183,239],"the":[9,38,46,73,84,98,109,116,121,128,131,141,145,149,158,170,181,197,208,215,226,237,240,248],"Reinforcement":[10],"Learning":[11],"(RL)":[12],"paradigm.":[13],"We":[14,68,95,113,201,229],"propose":[15],"three":[16,74],"fully":[17],"decentralized":[18],"multi-agent":[19,161,175],"natural":[20],"(MAN)":[22],"in":[24,174,207,211,218],"this":[25],"work.":[26],"The":[27],"objective":[28,110],"is":[29,106,125,169,222,243],"to":[30,53,60,77,87,108,195],"collectively":[31],"find":[32],"a":[33,49,64,78,191,232],"joint":[34],"policy":[35,132],"that":[36,97,115,140,156],"maximizes":[37],"average":[39,198,209,216],"long-term":[40],"return":[41],"these":[43,90],"agents.":[44],"In":[45],"absence":[47],"central":[50],"controller":[51],"and":[52],"preserve":[54],"privacy,":[55],"agents":[56],"communicate":[57],"some":[58],"information":[59,123],"their":[61],"neighbors":[62],"via":[63],"time-varying":[65],"communication":[66],"network.":[67],"prove":[69],"convergence":[70],"all":[72],"MAN":[75,150,213,220,241],"globally":[79],"asymptotically":[80],"stable":[81],"set":[82],"ODE":[85],"corresponding":[86],"actor":[88],"update;":[89],"use":[91],"linear":[92],"function":[93],"approximations.":[94],"show":[96,139],"Kullback\u2013Leibler":[99],"divergence":[100],"between":[101],"policies":[102],"successive":[104],"iterates":[105],"proportional":[107],"function\u2019s":[111],"gradient.":[112],"observe":[114,202],"minimum":[117],"singular":[118],"value":[119,143],"Fisher":[122],"matrix":[124],"well":[126],"within":[127],"reciprocal":[129],"parameter":[133],"dimension.":[134],"Using":[135],"this,":[136],"we":[137,187],"theoretically":[138],"optimal":[142],"deterministic":[146],"variant":[147],"algorithm":[151,221],"at":[152],"each":[153],"iterate":[154],"dominates":[155],"standard":[159],"gradient-based":[160],"(MAAC)":[163],"algorithm.":[164,228,250],"To":[165,179],"our":[166,184],"knowledge,":[167],"it":[168],"first":[171],"such":[172],"result":[173],"reinforcement":[176],"learning":[177],"(MARL).":[178],"illustrate":[180],"usefulness":[182],"proposed":[185],"algorithms,":[186],"implement":[188],"them":[189],"on":[190,223],"bi-lane":[192],"traffic":[193],"network":[194,199],"reduce":[196],"congestion.":[200],"almost":[204],"25%":[205],"reduction":[206],"congestion":[210,217],"2":[212],"algorithms;":[214],"another":[219],"par":[224],"with":[225],"MAAC":[227,249],"also":[230],"consider":[231],"generic":[233],"15":[234],"agent":[235],"MARL;":[236],"performance":[238],"again":[244],"as":[245,247],"good":[246]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}