{"id":"https://openalex.org/W4206318069","doi":"https://doi.org/10.1109/cog52621.2021.9619081","title":"Capacity-Limited Decentralized Actor-Critic for Multi-Agent Games","display_name":"Capacity-Limited Decentralized Actor-Critic for Multi-Agent Games","publication_year":2021,"publication_date":"2021-08-17","ids":{"openalex":"https://openalex.org/W4206318069","doi":"https://doi.org/10.1109/cog52621.2021.9619081"},"language":"en","primary_location":{"id":"doi:10.1109/cog52621.2021.9619081","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog52621.2021.9619081","pdf_url":null,"source":{"id":"https://openalex.org/S4363608335","display_name":"2021 IEEE Conference on Games (CoG)","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 IEEE Conference on Games (CoG)","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/A5006638341","display_name":"Tyler Malloy","orcid":"https://orcid.org/0000-0003-2512-984X"},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tyler Malloy","raw_affiliation_strings":["Cognitive Science Rensselaer Polytechnic Institute, Troy, NY, USA"],"affiliations":[{"raw_affiliation_string":"Cognitive Science Rensselaer Polytechnic Institute, Troy, NY, USA","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038964785","display_name":"Chris R. Sims","orcid":"https://orcid.org/0000-0002-3110-1686"},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chris R. Sims","raw_affiliation_strings":["Cognitive Science Rensselaer Polytechnic Institute, Troy, NY, USA"],"affiliations":[{"raw_affiliation_string":"Cognitive Science Rensselaer Polytechnic Institute, Troy, NY, USA","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074288533","display_name":"Tim Klinger","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tim Klinger","raw_affiliation_strings":["IBM Research AI, Yorktown, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research AI, Yorktown, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100348890","display_name":"Miao Liu","orcid":"https://orcid.org/0000-0002-0127-6899"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Miao Liu","raw_affiliation_strings":["IBM Research AI, Yorktown, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research AI, Yorktown, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037927240","display_name":"Matthew Riemer","orcid":null},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Riemer","raw_affiliation_strings":["Cognitive Science Rensselaer Polytechnic Institute, Troy, NY, USA"],"affiliations":[{"raw_affiliation_string":"Cognitive Science Rensselaer Polytechnic Institute, Troy, NY, USA","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113551673","display_name":"Gerald Tesauro","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gerald Tesauro","raw_affiliation_strings":["IBM Research AI, Yorktown, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research AI, Yorktown, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5006638341"],"corresponding_institution_ids":["https://openalex.org/I165799507"],"apc_list":null,"apc_paid":null,"fwci":0.2513,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.52533184,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T10646","display_name":"Experimental Behavioral Economics Studies","score":0.9929999709129333,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11182","display_name":"Auction Theory and Applications","score":0.9828000068664551,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7060106992721558},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6853342056274414},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.6751261353492737},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5490846037864685},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5232240557670593},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.4853028655052185},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4533197581768036},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43482452630996704},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.37770745158195496},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36051851511001587},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14577212929725647}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7060106992721558},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6853342056274414},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.6751261353492737},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5490846037864685},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5232240557670593},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.4853028655052185},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4533197581768036},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43482452630996704},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.37770745158195496},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36051851511001587},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14577212929725647},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cog52621.2021.9619081","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog52621.2021.9619081","pdf_url":null,"source":{"id":"https://openalex.org/S4363608335","display_name":"2021 IEEE Conference on Games (CoG)","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 IEEE Conference on Games (CoG)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2602275733","https://openalex.org/W2617547828","https://openalex.org/W2781726626","https://openalex.org/W2894976951","https://openalex.org/W2911616846","https://openalex.org/W2982316857","https://openalex.org/W3092485320","https://openalex.org/W3137166149","https://openalex.org/W4288088584","https://openalex.org/W4288109968","https://openalex.org/W4299802797","https://openalex.org/W6735650757","https://openalex.org/W6737849119","https://openalex.org/W6738796088","https://openalex.org/W6747473740","https://openalex.org/W6755069753","https://openalex.org/W6758518918","https://openalex.org/W6767141496","https://openalex.org/W6767866668","https://openalex.org/W6784310443","https://openalex.org/W6792167140"],"related_works":["https://openalex.org/W1574414179","https://openalex.org/W4362597605","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4297676672","https://openalex.org/W4281702477","https://openalex.org/W4378510483","https://openalex.org/W4376166922","https://openalex.org/W2490526372","https://openalex.org/W4221142204"],"abstract_inverted_index":{"This":[0],"paper":[1],"explores":[2],"information-theoretic":[3,122,145],"constraints":[4,146],"on":[5,147],"methods":[6,91],"for":[7],"multi-agent":[8,152],"reinforcement":[9],"learning":[10,28],"(MARL)":[11],"in":[12,71,76,92,134,159,165],"mixed":[13],"cooperative":[14,170],"and":[15,154],"competitive":[16,166],"games.":[17,171],"Within":[18],"this":[19,108],"domain,":[20],"decentralized":[21],"training":[22],"has":[23],"been":[24],"employed":[25],"to":[26,43,96,111,113,169],"increase":[27,70],"sample":[29],"efficiency.":[30],"However,":[31],"these":[32,144],"approaches":[33],"do":[34],"not":[35,65],"explicitly":[36],"discourage":[37],"complex":[38,60],"policies,":[39,106,132],"which":[40],"can":[41,109],"lead":[42,110],"overfitting.":[44],"To":[45,117],"address":[46],"this,":[47,119],"we":[48],"apply":[49],"an":[50,156],"information":[51],"theoretic":[52],"constraint":[53,123],"onto":[54,126],"agents'":[55,87,105,131],"policies":[56],"that":[57],"discourages":[58],"overly":[59],"behaviour":[61],"when":[62],"it":[63],"is":[64,78,124],"associated":[66],"with":[67,161],"a":[68,120,135,148],"significant":[69],"reward.":[72],"A":[73],"second":[74],"challenge":[75],"MARL":[77,93],"the":[79,82,98,127,141],"non-stationarity":[80,101],"of":[81,100,129,143,151],"environment":[83],"introduced":[84],"by":[85,102],"other":[86,104,130],"changing":[88],"policies.":[89],"Previous":[90],"have":[94],"sought":[95],"reduce":[97],"impact":[99],"inferring":[103],"but":[107],"over-fitting":[112],"previously":[114],"observed":[115],"behaviour.":[116],"avoid":[118],"similar":[121],"applied":[125],"inference":[128],"resulting":[133],"more":[136],"robust":[137],"estimate.":[138],"We":[139],"evaluate":[140],"effects":[142],"test":[149],"suite":[150],"games,":[153],"report":[155],"overall":[157],"improvement":[158],"performance,":[160],"greater":[162],"improvements":[163],"found":[164],"domains":[167],"compared":[168]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}