{"id":"https://openalex.org/W4210712114","doi":"https://doi.org/10.1109/cdc45484.2021.9682939","title":"Intermittent Communications in Decentralized Shadow Reward Actor-Critic","display_name":"Intermittent Communications in Decentralized Shadow Reward Actor-Critic","publication_year":2021,"publication_date":"2021-12-14","ids":{"openalex":"https://openalex.org/W4210712114","doi":"https://doi.org/10.1109/cdc45484.2021.9682939"},"language":"en","primary_location":{"id":"doi:10.1109/cdc45484.2021.9682939","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc45484.2021.9682939","pdf_url":null,"source":{"id":"https://openalex.org/S4363607724","display_name":"2021 60th IEEE 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":"2021 60th IEEE 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/A5039563144","display_name":"Amrit Singh Bedi","orcid":"https://orcid.org/0000-0002-8807-2695"},"institutions":[{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amrit Singh Bedi","raw_affiliation_strings":["U.S. Army Research Laboratory,Adelphi,MD,USA,20783"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"U.S. Army Research Laboratory,Adelphi,MD,USA,20783","institution_ids":["https://openalex.org/I166416128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025896653","display_name":"Alec Koppel","orcid":"https://orcid.org/0000-0003-2447-2873"},"institutions":[{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alec Koppel","raw_affiliation_strings":["U.S. Army Research Laboratory,Adelphi,MD,USA,20783"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"U.S. Army Research Laboratory,Adelphi,MD,USA,20783","institution_ids":["https://openalex.org/I166416128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100707460","display_name":"Mengdi Wang","orcid":"https://orcid.org/0000-0002-2101-9507"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mengdi Wang","raw_affiliation_strings":["Princeton University,Dept. of Electrical Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University,Dept. of Electrical Engineering","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101898224","display_name":"Junyu Zhang","orcid":"https://orcid.org/0000-0003-2194-9664"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junyu Zhang","raw_affiliation_strings":["Princeton University,Dept. of Electrical Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University,Dept. of Electrical Engineering","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.30599473,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"8","issue":null,"first_page":"2613","last_page":"2620"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12592","display_name":"Opinion Dynamics and Social Influence","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12592","display_name":"Opinion Dynamics and Social Influence","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9897000193595886,"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/T11031","display_name":"Game Theory and Applications","score":0.979200005531311,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/shadow","display_name":"Shadow (psychology)","score":0.6499559879302979},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5840714573860168},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3456883430480957},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.18628087639808655}],"concepts":[{"id":"https://openalex.org/C117797892","wikidata":"https://www.wikidata.org/wiki/Q286363","display_name":"Shadow (psychology)","level":2,"score":0.6499559879302979},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5840714573860168},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3456883430480957},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.18628087639808655},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc45484.2021.9682939","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc45484.2021.9682939","pdf_url":null,"source":{"id":"https://openalex.org/S4363607724","display_name":"2021 60th IEEE 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":"2021 60th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1518931405","https://openalex.org/W1643746074","https://openalex.org/W1918371733","https://openalex.org/W1974661392","https://openalex.org/W1977655452","https://openalex.org/W1986014385","https://openalex.org/W1995985801","https://openalex.org/W2044212084","https://openalex.org/W2086304253","https://openalex.org/W2099618002","https://openalex.org/W2117905067","https://openalex.org/W2119717200","https://openalex.org/W2128928412","https://openalex.org/W2155027007","https://openalex.org/W2294586855","https://openalex.org/W2414837766","https://openalex.org/W2492629073","https://openalex.org/W2788115019","https://openalex.org/W2799544270","https://openalex.org/W2902298341","https://openalex.org/W2904435756","https://openalex.org/W2913483008","https://openalex.org/W2947958009","https://openalex.org/W2963322416","https://openalex.org/W2964005211","https://openalex.org/W2964339512","https://openalex.org/W2982316857","https://openalex.org/W3035578948","https://openalex.org/W3038915804","https://openalex.org/W3102899483","https://openalex.org/W3160598148","https://openalex.org/W3167041099","https://openalex.org/W4298023569","https://openalex.org/W4299802797","https://openalex.org/W6643772956","https://openalex.org/W6683204974","https://openalex.org/W6738796088","https://openalex.org/W6749032143","https://openalex.org/W6751921135","https://openalex.org/W6757058172","https://openalex.org/W6757082500","https://openalex.org/W6758960857","https://openalex.org/W6762191990","https://openalex.org/W6773677875","https://openalex.org/W6780383567","https://openalex.org/W6780386840","https://openalex.org/W6795539215"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2893218741","https://openalex.org/W4392589133","https://openalex.org/W2390279801","https://openalex.org/W2558319350","https://openalex.org/W1492594177","https://openalex.org/W2358668433","https://openalex.org/W1842742976","https://openalex.org/W4396701345"],"abstract_inverted_index":{"Broader":[0],"decision-making":[1],"goals":[2],"such":[3],"as":[4],"risk-sensitivity,":[5],"exploration,":[6],"and":[7,100,145,163],"incorporating":[8],"prior":[9],"experience":[10],"motivates":[11],"the":[12,22,29,41,113,129,132,142,146,189],"study":[13],"of":[14,28,131,148,191],"cooperative":[15,199],"multi-agent":[16],"reinforcement":[17],"learning":[18],"(MARL)":[19],"problems":[20],"where":[21],"objective":[23],"is":[24,110,125],"any":[25],"nonlinear":[26],"function":[27],"team\u2019s":[30],"long-term":[31],"state-action":[32],"occupancy":[33,120,139],"measure,":[34,140],"i.e.,":[35,141],"a":[36],"general":[37],"utility,":[38],"which":[39,59,124],"subsumes":[40],"aforementioned":[42],"goals.":[43],"Existing":[44],"decentralized":[45],"actor-critic":[46],"algorithms":[47],"to":[48,88,127,137,165],"solve":[49],"this":[50,192],"problem":[51],"require":[52,169],"extensive":[53],"message":[54],"passing":[55],"per":[56],"policy":[57,91,106],"update,":[58],"may":[60,74],"be":[61],"impractical.":[62],"Thus,":[63],"we":[64,168],"put":[65],"forth":[66],"Communication-Efficient":[67],"Decentralized":[68],"Shadow":[69],"Reward":[70],"Actor-Critic":[71],"(CE-DSAC)":[72],"that":[73],"operate":[75],"with":[76,96,135,184,202],"time-varying":[77],"or":[78,176],"event-triggered":[79],"network":[80],"connectivities.":[81],"This":[82,156],"scheme":[83,157],"operates":[84],"by":[85,154],"having":[86],"agents":[87,197],"alternate":[89],"between":[90,161],"evaluation":[92],"(critic),":[93],"weighted":[94,150],"averaging":[95,151],"neighbors":[97],"(information":[98],"mixing),":[99],"local":[101,119,133,149],"gradient":[102],"updates":[103],"for":[104,194],"their":[105,138],"parameters":[107],"(actor).":[108],"CE-DSAC":[109],"different":[111],"from":[112],"usual":[114],"critic":[115],"update":[116],"in":[117,170],"its":[118],"measure":[121],"estimation":[122],"step":[123],"needed":[126],"estimate":[128],"derivative":[130],"utility":[134],"respect":[136],"\"shadow":[143],"reward,\"":[144],"amount":[147],"steps":[152,183],"executed":[153],"agents.":[155],"improves":[158],"existing":[159],"tradeoffs":[160],"communications":[162],"convergence:":[164],"obtain":[166],"\u03f5-stationarity,":[167],"${\\mathcal{O}}\\left({1/{":[171,178],"\\in":[172,179],"^{2.5}}}\\right)$":[173],"(Theorem":[174],"IV.6)":[175],"faster":[177],"^2}}\\right)$":[180],"(Corollary":[181],"IV.8)":[182],"high":[185],"probability.":[186],"Experiments":[187],"demonstrate":[188],"merits":[190],"approach":[193],"multiple":[195],"RL":[196],"solving":[198],"navigation":[200],"tasks":[201],"intermittent":[203],"communications.":[204]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}