{"id":"https://openalex.org/W3200847968","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533333","title":"Distributed Emergent Agreements with Deep Reinforcement Learning","display_name":"Distributed Emergent Agreements with Deep Reinforcement Learning","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3200847968","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533333","mag":"3200847968"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9533333","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533333","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","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/A5061867637","display_name":"Kyrill Schmid","orcid":null},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kyrill Schmid","raw_affiliation_strings":["Ludwig-Maximilians-Universit\u00e4t, M\u00fcnchen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ludwig-Maximilians-Universit\u00e4t, M\u00fcnchen","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052914309","display_name":"Robert M\u00fcller","orcid":"https://orcid.org/0000-0003-3108-713X"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Robert Muller","raw_affiliation_strings":["Ludwig-Maximilians-Universit\u00e4t, M\u00fcnchen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ludwig-Maximilians-Universit\u00e4t, M\u00fcnchen","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068564686","display_name":"Lenz Belzner","orcid":"https://orcid.org/0009-0002-4683-5460"},"institutions":[{"id":"https://openalex.org/I4210086764","display_name":"Dr. August Wolff (Germany)","ror":"https://ror.org/000m3hy37","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210086764"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lenz Belzner","raw_affiliation_strings":["Maiborn Wolff GmbH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Maiborn Wolff GmbH","institution_ids":["https://openalex.org/I4210086764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045118231","display_name":"Johannes Tochtermann","orcid":null},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Johannes Tochtermann","raw_affiliation_strings":["Ludwig-Maximilians-Universit\u00e4t, M\u00fcnchen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ludwig-Maximilians-Universit\u00e4t, M\u00fcnchen","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022303989","display_name":"Claudia Linhoff-Popien","orcid":null},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Claudia Linhoff-Popien","raw_affiliation_strings":["Ludwig-Maximilians-Universit\u00e4t, M\u00fcnchen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ludwig-Maximilians-Universit\u00e4t, M\u00fcnchen","institution_ids":["https://openalex.org/I8204097"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2799,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.64571516,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"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":0.9991000294685364,"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":0.9991000294685364,"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/T10270","display_name":"Blockchain Technology Applications and Security","score":0.9873999953269958,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11182","display_name":"Auction Theory and Applications","score":0.9667999744415283,"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":0.8394469022750854},{"id":"https://openalex.org/keywords/commit","display_name":"Commit","score":0.7483260631561279},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.743850588798523},{"id":"https://openalex.org/keywords/autonomous-agent","display_name":"Autonomous agent","score":0.5109635591506958},{"id":"https://openalex.org/keywords/profit","display_name":"Profit (economics)","score":0.4990406036376953},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.44642943143844604},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4370640516281128},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.43614470958709717},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3908127248287201},{"id":"https://openalex.org/keywords/microeconomics","display_name":"Microeconomics","score":0.14403298497200012},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.08970612287521362}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8394469022750854},{"id":"https://openalex.org/C153180980","wikidata":"https://www.wikidata.org/wiki/Q19776675","display_name":"Commit","level":2,"score":0.7483260631561279},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.743850588798523},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.5109635591506958},{"id":"https://openalex.org/C181622380","wikidata":"https://www.wikidata.org/wiki/Q26911","display_name":"Profit (economics)","level":2,"score":0.4990406036376953},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.44642943143844604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4370640516281128},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.43614470958709717},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3908127248287201},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.14403298497200012},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.08970612287521362},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9533333","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533333","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1515851193","https://openalex.org/W1542941925","https://openalex.org/W1562353621","https://openalex.org/W2028145673","https://openalex.org/W2143362857","https://openalex.org/W2145339207","https://openalex.org/W2176412452","https://openalex.org/W2395575420","https://openalex.org/W2487898712","https://openalex.org/W2594794854","https://openalex.org/W2617547828","https://openalex.org/W2626637010","https://openalex.org/W2736601468","https://openalex.org/W2739364177","https://openalex.org/W2791207714","https://openalex.org/W2891661335","https://openalex.org/W2950993296","https://openalex.org/W2962938168","https://openalex.org/W2963000099","https://openalex.org/W2963285578","https://openalex.org/W2963407617","https://openalex.org/W2963627051","https://openalex.org/W2963689090","https://openalex.org/W2964345382","https://openalex.org/W2991046523","https://openalex.org/W3093287223","https://openalex.org/W3110959560","https://openalex.org/W4287552525","https://openalex.org/W4295150809","https://openalex.org/W4295598622","https://openalex.org/W4297627396","https://openalex.org/W4299802797","https://openalex.org/W6681625305","https://openalex.org/W6685562342","https://openalex.org/W6712181171","https://openalex.org/W6735011893","https://openalex.org/W6737849119","https://openalex.org/W6738796088","https://openalex.org/W6739516088","https://openalex.org/W6741002519","https://openalex.org/W6741436713","https://openalex.org/W6744562401","https://openalex.org/W6748981803","https://openalex.org/W6749304979","https://openalex.org/W6754779100","https://openalex.org/W6771274123","https://openalex.org/W6786981901"],"related_works":["https://openalex.org/W4206233823","https://openalex.org/W2494202692","https://openalex.org/W2161520603","https://openalex.org/W2612836981","https://openalex.org/W2604958989","https://openalex.org/W2618716983","https://openalex.org/W2032491180","https://openalex.org/W2620638075","https://openalex.org/W1586030051","https://openalex.org/W2372480026"],"abstract_inverted_index":{"Building":[0],"autonomous":[1],"agents":[2,28,48,60,82,94,115],"that":[3,53,150],"are":[4],"capable":[5],"to":[6,42,86,95,101,116,118,130],"cooperate":[7,102],"with":[8,29,83,89,103,128],"other":[9,104],"machines":[10],"is":[11,57],"an":[12],"essential":[13],"step":[14],"towards":[15],"large":[16],"scale":[17],"application":[18],"of":[19,25,139],"AI":[20],"systems.":[21],"Especially":[22],"systems":[23],"comprised":[24],"multiple":[26],"self-interested":[27],"general":[30],"sum":[31],"returns":[32],"can":[33,40],"profit":[34],"from":[35,46],"cooperative":[36],"behavior":[37],"as":[38,134],"cooperation":[39,56,153],"help":[41],"increase":[43,152],"the":[44,84,123],"return":[45],"all":[47],"simultaneously.":[49],"A":[50],"critical":[51],"aspect":[52],"might":[54],"undermine":[55],"given":[58],"if":[59],"cannot":[61],"make":[62],"credible":[63],"threats":[64],"or":[65,137],"promises":[66],"(called":[67],"commitment":[68],"problems).":[69],"Inspired":[70],"by":[71,122,154],"this":[72,75],"idea":[73],"in":[74,143],"work":[76],"we":[77],"augment":[78],"deep":[79],"reinforcement":[80],"learning":[81,112],"capability":[85],"build":[87],"agreements":[88,151],"one":[90],"another,":[91],"thereby":[92],"enabling":[93],"autonomously":[96],"learn":[97],"at":[98],"which":[99],"time":[100],"agents.":[105],"This":[106],"approach,":[107],"called":[108],"distributed":[109],"emergent":[110],"agreement":[111],"(DEAL),":[113],"enables":[114],"commit":[117],"specific":[119],"policies":[120],"defined":[121],"agreement.":[124],"We":[125],"evaluate":[126],"DEAL":[127],"up":[129],"16":[131],"agents,":[132],"represented":[133],"Deep":[135],"Q-Networks":[136],"instances":[138],"Proximal":[140],"Policy":[141],"Optimization":[142],"a":[144],"factory":[145],"domain":[146],"and":[147,158],"empirically":[148],"show":[149],"improving":[155],"both":[156],"overall":[157],"agent":[159],"individual":[160],"returns.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}