{"id":"https://openalex.org/W4312883490","doi":"https://doi.org/10.1109/case49997.2022.9926587","title":"A Reinforcement Learning Decentralized Multi-Agent Control Approach exploiting Cognitive Cooperation on Continuous Environments","display_name":"A Reinforcement Learning Decentralized Multi-Agent Control Approach exploiting Cognitive Cooperation on Continuous Environments","publication_year":2022,"publication_date":"2022-08-20","ids":{"openalex":"https://openalex.org/W4312883490","doi":"https://doi.org/10.1109/case49997.2022.9926587"},"language":"en","primary_location":{"id":"doi:10.1109/case49997.2022.9926587","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case49997.2022.9926587","pdf_url":null,"source":{"id":"https://openalex.org/S4363607892","display_name":"2022 IEEE 18th International Conference on Automation Science and Engineering (CASE)","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 18th International Conference on Automation Science and Engineering (CASE)","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/A5045174051","display_name":"Gerardo Camacho-Gonzalez","orcid":"https://orcid.org/0000-0001-9850-2524"},"institutions":[{"id":"https://openalex.org/I162290304","display_name":"Scuola Superiore Sant'Anna","ror":"https://ror.org/025602r80","country_code":"IT","type":"education","lineage":["https://openalex.org/I162290304"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Gerardo Camacho-Gonzalez","raw_affiliation_strings":["Institute of Mechanical Intelligence, Scuola Superiore Sant’Anna,Perceptual Robotics Laboratory,Department of Excellence in Robotics & AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Mechanical Intelligence, Scuola Superiore Sant’Anna,Perceptual Robotics Laboratory,Department of Excellence in Robotics & AI","institution_ids":["https://openalex.org/I162290304"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011817358","display_name":"Salvatore D\u2019Avella","orcid":"https://orcid.org/0000-0001-7065-8789"},"institutions":[{"id":"https://openalex.org/I162290304","display_name":"Scuola Superiore Sant'Anna","ror":"https://ror.org/025602r80","country_code":"IT","type":"education","lineage":["https://openalex.org/I162290304"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Salvatore D'Avella","raw_affiliation_strings":["Institute of Mechanical Intelligence, Scuola Superiore Sant’Anna,Perceptual Robotics Laboratory,Department of Excellence in Robotics & AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Mechanical Intelligence, Scuola Superiore Sant’Anna,Perceptual Robotics Laboratory,Department of Excellence in Robotics & AI","institution_ids":["https://openalex.org/I162290304"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086535808","display_name":"Carlo Alberto Avizzano","orcid":"https://orcid.org/0000-0001-5802-541X"},"institutions":[{"id":"https://openalex.org/I162290304","display_name":"Scuola Superiore Sant'Anna","ror":"https://ror.org/025602r80","country_code":"IT","type":"education","lineage":["https://openalex.org/I162290304"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Carlo A. Avizzano","raw_affiliation_strings":["Institute of Mechanical Intelligence, Scuola Superiore Sant’Anna,Perceptual Robotics Laboratory,Department of Excellence in Robotics & AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Mechanical Intelligence, Scuola Superiore Sant’Anna,Perceptual Robotics Laboratory,Department of Excellence in Robotics & AI","institution_ids":["https://openalex.org/I162290304"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021769360","display_name":"Paolo Tripicchio","orcid":"https://orcid.org/0000-0003-3225-2782"},"institutions":[{"id":"https://openalex.org/I162290304","display_name":"Scuola Superiore Sant'Anna","ror":"https://ror.org/025602r80","country_code":"IT","type":"education","lineage":["https://openalex.org/I162290304"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Paolo Tripicchio","raw_affiliation_strings":["Institute of Mechanical Intelligence, Scuola Superiore Sant’Anna,Perceptual Robotics Laboratory,Department of Excellence in Robotics & AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Mechanical Intelligence, Scuola Superiore Sant’Anna,Perceptual Robotics Laboratory,Department of Excellence in Robotics & AI","institution_ids":["https://openalex.org/I162290304"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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":0.17015637,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1557","last_page":"1562"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.992900013923645,"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":0.992900013923645,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.972599983215332,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9513999819755554,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8845042586326599},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7684202194213867},{"id":"https://openalex.org/keywords/avatar","display_name":"Avatar","score":0.6228272318840027},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6042255759239197},{"id":"https://openalex.org/keywords/autonomous-agent","display_name":"Autonomous agent","score":0.5724205374717712},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5074223875999451},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5022785663604736},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.46363207697868347},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4465149939060211},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4329172968864441},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.42599812150001526},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4068562388420105},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13145595788955688}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8845042586326599},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7684202194213867},{"id":"https://openalex.org/C2777365542","wikidata":"https://www.wikidata.org/wiki/Q83090","display_name":"Avatar","level":2,"score":0.6228272318840027},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6042255759239197},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.5724205374717712},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5074223875999451},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5022785663604736},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.46363207697868347},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4465149939060211},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4329172968864441},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.42599812150001526},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4068562388420105},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13145595788955688},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/case49997.2022.9926587","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case49997.2022.9926587","pdf_url":null,"source":{"id":"https://openalex.org/S4363607892","display_name":"2022 IEEE 18th International Conference on Automation Science and Engineering (CASE)","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 18th International Conference on Automation Science and Engineering (CASE)","raw_type":"proceedings-article"},{"id":"pmh:oai:www.iris.sssup.it:11382/551153","is_oa":false,"landing_page_url":"https://hdl.handle.net/11382/551153","pdf_url":null,"source":{"id":"https://openalex.org/S4377196376","display_name":"CINECA IRIS Institutional Research Information System (Sant'Anna School of Advanced Studies)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I162290304","host_organization_name":"Scuola Superiore Sant'Anna","host_organization_lineage":["https://openalex.org/I162290304"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17","score":0.5}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"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":{"Multi-agent":[0],"system":[1],"control":[2,28,63,82],"is":[3,21,100,139],"a":[4,27,60,67,83,104,116,148,186,210],"research":[5],"topic":[6],"that":[7],"has":[8,192],"broad":[9],"applications":[10],"ranging":[11],"from":[12,49],"multi-robot":[13],"cooperation":[14],"to":[15,23,89,93,112,125,128,159,168,171],"distributed":[16],"sensor":[17],"networks.":[18],"Reinforcement":[19],"learning":[20,71],"shown":[22],"be":[24,169],"promising":[25],"as":[26],"strategy":[29],"in":[30,73,110,177,195,209],"cases":[31],"where":[32],"the":[33,36,79,95,107,121,131,152,156,162,204,215],"dynamics":[34],"of":[35,98,106,151],"agents":[37,123],"are":[38],"non-linear,":[39],"complex,":[40],"and":[41,109,154,198,203],"highly":[42],"uncertain":[43],"since":[44,143],"it":[45,144],"can":[46],"learn":[47],"policies":[48],"samples":[50],"without":[51],"using":[52,214],"much":[53],"model":[54],"information.":[55],"The":[56,164,201],"presented":[57],"manuscript":[58],"proposes":[59],"multi-agent":[61,69],"decentralized":[62],"approach":[64,166],"based":[65],"on":[66,130],"new":[68],"reinforcement":[70],"setting":[72],"which":[74],"two":[75,178],"virtual":[76,122,135],"agents,":[77],"sharing":[78],"same":[80],"environment,":[81],"single":[84],"avatar":[85],"but":[86,127],"have":[87,147,206],"access":[88],"complementary":[90],"details":[91],"necessary":[92],"finish":[94],"task.":[96],"Each":[97,134],"them":[99],"responsible":[101],"for":[102],"solving":[103],"portion":[105],"problem,":[108],"order":[111],"efficiently":[113,173],"solve":[114,172],"it,":[115],"collaboration":[117],"should":[118],"emerge":[119],"among":[120],"not":[124,140,146],"compete":[126],"focus":[129],"final":[132],"goal.":[133],"agent,":[136],"performing":[137],"individually,":[138],"fully":[141],"autonomous":[142],"does":[145],"complete":[149],"vision":[150],"scene":[153],"needs":[155],"other":[157],"one":[158],"properly":[160],"command":[161],"avatar.":[163],"proposed":[165],"proved":[167],"able":[170],"constrained":[174],"navigation":[175],"problems":[176],"different":[179],"simulated":[180],"setups.":[181],"An":[182],"actor-critic":[183],"architecture":[184],"with":[185],"Proximal":[187],"Policy":[188],"Optimization":[189],"(PPO)":[190],"algorithm":[191],"been":[193,207],"employed":[194],"continuous":[196],"action":[197],"state":[199],"spaces.":[200],"training":[202],"testing":[205],"done":[208],"maze-like":[211],"environment":[212],"designed":[213],"StarCraft":[216],"II":[217],"Learning":[218],"Environment.":[219]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}