{"id":"https://openalex.org/W2560702874","doi":"https://doi.org/10.1017/s026988891500020x","title":"A reinforcement learning approach to coordinate exploration with limited communication in continuous action games","display_name":"A reinforcement learning approach to coordinate exploration with limited communication in continuous action games","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2560702874","doi":"https://doi.org/10.1017/s026988891500020x","mag":"2560702874"},"language":"en","primary_location":{"id":"doi:10.1017/s026988891500020x","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s026988891500020x","pdf_url":null,"source":{"id":"https://openalex.org/S137506714","display_name":"The Knowledge Engineering Review","issn_l":"0269-8889","issn":["0269-8889","1469-8005"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Knowledge Engineering Review","raw_type":"journal-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/A5080960061","display_name":"Abdel Rodr\u00edguez","orcid":"https://orcid.org/0000-0001-8840-3055"},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Abdel Rodr\u00edguez","raw_affiliation_strings":["Computational Modeling Lab, Vrije Universiteit Brussel \u2013 Pleinlaan 2, 1050 Brussels, Belgium e-mail:","Vrije Universiteit Brussel \u2013 Pleinlaan 2"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Modeling Lab, Vrije Universiteit Brussel \u2013 Pleinlaan 2, 1050 Brussels, Belgium e-mail:","institution_ids":["https://openalex.org/I13469542"]},{"raw_affiliation_string":"Vrije Universiteit Brussel \u2013 Pleinlaan 2","institution_ids":["https://openalex.org/I13469542"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062896285","display_name":"Peter Vrancx","orcid":"https://orcid.org/0000-0002-9876-3684"},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Peter Vrancx","raw_affiliation_strings":["Computational Modeling Lab, Vrije Universiteit Brussel \u2013 Pleinlaan 2, 1050 Brussels, Belgium e-mail:","Vrije Universiteit Brussel \u2013 Pleinlaan 2"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Modeling Lab, Vrije Universiteit Brussel \u2013 Pleinlaan 2, 1050 Brussels, Belgium e-mail:","institution_ids":["https://openalex.org/I13469542"]},{"raw_affiliation_string":"Vrije Universiteit Brussel \u2013 Pleinlaan 2","institution_ids":["https://openalex.org/I13469542"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110010814","display_name":"Ricardo Grau","orcid":null},"institutions":[{"id":"https://openalex.org/I3018837529","display_name":"Universidad Central \"Marta Abreu\" de las Villas (UCLV)","ror":"https://ror.org/01cdy6h50","country_code":"CU","type":"education","lineage":["https://openalex.org/I3018837529"]},{"id":"https://openalex.org/I4210108197","display_name":"Universidad Central","ror":"https://ror.org/01kyyzm82","country_code":"BO","type":"education","lineage":["https://openalex.org/I4210108197"]}],"countries":["BO","CU"],"is_corresponding":false,"raw_author_name":"Ricardo Grau","raw_affiliation_strings":["Center of Studies in Informatics, Universidad Central \u2018Marta Abreu\u2019 de Las Villas \u2013 Carretera a Camajuan\u00ed Km 5, 50100 Villa Clara, Cuba e-mail:","Universidad Central \u2018Marta Abreu\u2019 de Las Villas \u2013 Carretera a Camajuan\u00ed Km 5"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center of Studies in Informatics, Universidad Central \u2018Marta Abreu\u2019 de Las Villas \u2013 Carretera a Camajuan\u00ed Km 5, 50100 Villa Clara, Cuba e-mail:","institution_ids":["https://openalex.org/I4210108197","https://openalex.org/I3018837529"]},{"raw_affiliation_string":"Universidad Central \u2018Marta Abreu\u2019 de Las Villas \u2013 Carretera a Camajuan\u00ed Km 5","institution_ids":["https://openalex.org/I3018837529"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064553018","display_name":"Ann Now\u00e9","orcid":"https://orcid.org/0000-0001-6346-4564"},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Ann Now\u00e9","raw_affiliation_strings":["Computational Modeling Lab, Vrije Universiteit Brussel \u2013 Pleinlaan 2, 1050 Brussels, Belgium e-mail:","Vrije Universiteit Brussel \u2013 Pleinlaan 2"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Modeling Lab, Vrije Universiteit Brussel \u2013 Pleinlaan 2, 1050 Brussels, Belgium e-mail:","institution_ids":["https://openalex.org/I13469542"]},{"raw_affiliation_string":"Vrije Universiteit Brussel \u2013 Pleinlaan 2","institution_ids":["https://openalex.org/I13469542"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5080960061"],"corresponding_institution_ids":["https://openalex.org/I13469542"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.14752798,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"31","issue":"1","first_page":"77","last_page":"95"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9994000196456909,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980999827384949,"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/T10675","display_name":"Mechanical Circulatory Support Devices","score":0.9603000283241272,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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":0.8334401845932007},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7275800108909607},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6473063230514526},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.5866320133209229},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5599198937416077},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4821590781211853},{"id":"https://openalex.org/keywords/learning-automata","display_name":"Learning automata","score":0.47671765089035034},{"id":"https://openalex.org/keywords/automaton","display_name":"Automaton","score":0.4690673053264618},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.46371033787727356},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4453507363796234},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.42402881383895874},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4153207242488861},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3721722364425659}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8334401845932007},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7275800108909607},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6473063230514526},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.5866320133209229},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5599198937416077},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4821590781211853},{"id":"https://openalex.org/C2776807809","wikidata":"https://www.wikidata.org/wiki/Q6510160","display_name":"Learning automata","level":3,"score":0.47671765089035034},{"id":"https://openalex.org/C112505250","wikidata":"https://www.wikidata.org/wiki/Q787116","display_name":"Automaton","level":2,"score":0.4690673053264618},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.46371033787727356},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4453507363796234},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.42402881383895874},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4153207242488861},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3721722364425659},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1017/s026988891500020x","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s026988891500020x","pdf_url":null,"source":{"id":"https://openalex.org/S137506714","display_name":"The Knowledge Engineering Review","issn_l":"0269-8889","issn":["0269-8889","1469-8005"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Knowledge Engineering Review","raw_type":"journal-article"},{"id":"pmh:oai:vubissmart:VUBISSMART:2000:87524","is_oa":false,"landing_page_url":"https://biblio.vub.ac.be/vubir/a-reinforcement-learning-approach-to-coordinate-exploration-with-limited-communication-in-continuous-action-games(d73aa661-2a24-49a4-8151-d5e7463af0e2).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306402573","display_name":"VUBIR (Vrije Universiteit Brussel)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I13469542","host_organization_name":"Vrije Universiteit Brussel","host_organization_lineage":["https://openalex.org/I13469542"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1574638321","https://openalex.org/W1575017126","https://openalex.org/W1825174002","https://openalex.org/W1975113431","https://openalex.org/W2010835231","https://openalex.org/W2024303516","https://openalex.org/W2045276965","https://openalex.org/W2076967360","https://openalex.org/W2104602264","https://openalex.org/W2124280092","https://openalex.org/W2132522159","https://openalex.org/W2158113413","https://openalex.org/W2292418659","https://openalex.org/W2397160369","https://openalex.org/W2484003876","https://openalex.org/W2583413467","https://openalex.org/W3023069629","https://openalex.org/W3139633029","https://openalex.org/W3149412023","https://openalex.org/W4206670532","https://openalex.org/W4230394883","https://openalex.org/W4236589009","https://openalex.org/W6634506789"],"related_works":["https://openalex.org/W2015051472","https://openalex.org/W2168501056","https://openalex.org/W2288872327","https://openalex.org/W2120009678","https://openalex.org/W2912947802","https://openalex.org/W2489338148","https://openalex.org/W2037601570","https://openalex.org/W2124961391","https://openalex.org/W2123856982","https://openalex.org/W2164265465"],"abstract_inverted_index":{"Abstract":[0],"Learning":[1],"automata":[2,42],"are":[3],"reinforcement":[4,40],"learners":[5],"belonging":[6],"to":[7,18,82,102,125],"the":[8,51,69,84,107,121,127,131],"class":[9],"of":[10,27,53,68,77,106,123,130,140],"policy":[11],"iterators.":[12],"They":[13],"have":[14],"already":[15],"been":[16],"shown":[17],"exhibit":[19],"nice":[20],"convergence":[21],"properties":[22],"in":[23,56,88,137],"a":[24,33,37,62,75,103,114,138],"wide":[25],"range":[26],"discrete":[28],"action":[29,39,58,87,109],"game":[30],"settings.":[31,91],"Recently,":[32],"new":[34],"formulation":[35],"for":[36,65,116],"continuous":[38,57,108],"learning":[41],"(CARLA)":[43],"was":[44],"proposed.":[45],"In":[46],"this":[47],"paper,":[48],"we":[49],"study":[50],"behavior":[52],"these":[54],"CARLA":[55,99],"games":[59],"and":[60],"propose":[61],"novel":[63],"method":[64,73,115],"coordinated":[66,117],"exploration":[67,118],"joint-action":[70],"space.":[71],"Our":[72],"allows":[74,120],"team":[76,122],"independent":[78,96],"learners,":[79],"using":[80,98],"CARLA,":[81],"find":[83,126],"optimal":[85],"joint":[86],"common":[89],"interest":[90],"We":[92,111,133],"first":[93],"show":[94],"that":[95],"agents":[97,124],"will":[100],"converge":[101],"local":[104],"optimum":[105,129],"game.":[110,132],"then":[112],"introduce":[113],"which":[119],"global":[128],"validate":[134],"our":[135],"approach":[136],"number":[139],"experiments.":[141]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}