{"id":"https://openalex.org/W1744965757","doi":null,"title":"A survey on multiagent reinforcement learning towards multi-robot systems","display_name":"A survey on multiagent reinforcement learning towards multi-robot systems","publication_year":2005,"publication_date":"2005-12-01","ids":{"openalex":"https://openalex.org/W1744965757","mag":"1744965757"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.122.3529","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.122.3529","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://csapps.essex.ac.uk/cig/2005/papers/p1012.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5022264324","display_name":"Erfu Yang","orcid":"https://orcid.org/0000-0003-1813-5950","observed_orcids":["https://orcid.org/0000-0003-1813-5950"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Erfu Yang","raw_affiliation_strings":["Design, Manufacture And Engineering Management"],"raw_orcid":"https://orcid.org/0000-0003-1813-5950","affiliations":[{"raw_affiliation_string":"Design, Manufacture And Engineering Management","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076389260","display_name":"Dongbing Gu","orcid":"https://orcid.org/0000-0002-0986-2921","observed_orcids":["https://orcid.org/0000-0002-0986-2921"]},"institutions":[{"id":"https://openalex.org/I110002522","display_name":"University of Essex","ror":"https://ror.org/02nkf1q06","country_code":"GB","type":"education","lineage":["https://openalex.org/I110002522"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dongbing Gu","raw_affiliation_strings":["University of Essex **"],"raw_orcid":"https://orcid.org/0000-0002-0986-2921","affiliations":[{"raw_affiliation_string":"University of Essex **","institution_ids":["https://openalex.org/I110002522"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.333,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.64048609,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"292","last_page":"299"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/multi-agent-reinforcement-learning","display_name":"multi-agent reinforcement learning","score":0.9750000238418579},{"id":"https://openalex.org/keywords/multi-robot-systems","display_name":"multi-robot systems","score":0.9990000128746033},{"id":"https://openalex.org/keywords/scalability","display_name":"scalability","score":0.6830000281333923},{"id":"https://openalex.org/keywords/distributed-reinforcement-learning","display_name":"distributed reinforcement learning","score":0.5680000185966492},{"id":"https://openalex.org/keywords/multi-robot-coordination","display_name":"multi-robot coordination","score":0.6399999856948853}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8862485885620117},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6489994525909424},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6300565004348755},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.62255859375},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5833827257156372},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5707446932792664},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.562785267829895},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.122.3529","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.122.3529","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://csapps.essex.ac.uk/cig/2005/papers/p1012.pdf","raw_type":"text"},{"id":"mag:1744965757","doi":null,"is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/conf/cig/cig2005.html#YangG05","pdf_url":null,"source":{"id":"https://openalex.org/S4306417932","display_name":"Computational Intelligence and Games","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Computational Intelligence and Games","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W400269483","https://openalex.org/W1484740474","https://openalex.org/W1490782493","https://openalex.org/W1493919947","https://openalex.org/W1497847676","https://openalex.org/W1504193820","https://openalex.org/W1507591516","https://openalex.org/W1513468570","https://openalex.org/W1519783625","https://openalex.org/W1537215075","https://openalex.org/W1542941925","https://openalex.org/W1546266526","https://openalex.org/W1548889916","https://openalex.org/W1564711114","https://openalex.org/W1569077671","https://openalex.org/W1573854133","https://openalex.org/W1575327902","https://openalex.org/W1578630563","https://openalex.org/W1580890024","https://openalex.org/W1588797187","https://openalex.org/W1595300949","https://openalex.org/W1605188341","https://openalex.org/W1626977535","https://openalex.org/W1800962324","https://openalex.org/W1933162220","https://openalex.org/W1936096975","https://openalex.org/W1966224968","https://openalex.org/W1967981236","https://openalex.org/W1971173632","https://openalex.org/W1973039793","https://openalex.org/W1999250483","https://openalex.org/W2065821056","https://openalex.org/W2089415692","https://openalex.org/W2095989982","https://openalex.org/W2103561211","https://openalex.org/W2103791569","https://openalex.org/W2104602264","https://openalex.org/W2112254845","https://openalex.org/W2115192345","https://openalex.org/W2119120935","https://openalex.org/W2120327309","https://openalex.org/W2120405980","https://openalex.org/W2120846115","https://openalex.org/W2121863487","https://openalex.org/W2139712289","https://openalex.org/W2143490508","https://openalex.org/W2147492008","https://openalex.org/W2155027007","https://openalex.org/W2167261463","https://openalex.org/W2171732592","https://openalex.org/W2936405433"],"related_works":["https://openalex.org/W56117469","https://openalex.org/W2054432309","https://openalex.org/W7098557977","https://openalex.org/W4412645405","https://openalex.org/W3142663663","https://openalex.org/W2186803321","https://openalex.org/W2377861520","https://openalex.org/W4362519817","https://openalex.org/W7100417991","https://openalex.org/W1493673339"],"abstract_inverted_index":{"Abstract-":[0],"Multiagent":[1],"reinforcement":[2,53,71],"learning":[3,54,72],"for":[4],"multirobot":[5],"systems":[6],"is":[7,64,99],"a":[8,32,67],"challenging":[9,92],"issue":[10],"in":[11,22,49,73,88],"both":[12],"robotics":[13],"and":[14,25],"artificial":[15],"intelligence.":[16],"With":[17],"the":[18,78,80,102,105],"ever":[19],"increasing":[20],"interests":[21],"theoretical":[23],"research":[24],"practical":[26],"applications,":[27],"currently":[28],"there":[29,44],"have":[30],"been":[31],"lot":[33],"of":[34,61,104],"efforts":[35],"towards":[36],"providing":[37],"some":[38,85,91],"solutions":[39],"to":[40,55,65],"this":[41,62,89],"challenge.":[42],"However,":[43],"are":[45,94],"still":[46],"many":[47],"difficulties":[48],"scaling":[50],"up":[51],"multiagent":[52,70],"multi-robot":[56,74],"systems.":[57],"The":[58],"main":[59],"objective":[60],"paper":[63],"provide":[66],"survey":[68],"on":[69,77],"systems,":[75],"based":[76],"literature":[79],"authors":[81],"collected.":[82],"After":[83],"reviewing":[84],"important":[86],"advances":[87],"field,":[90],"problems":[93],"analyzed.":[95],"A":[96],"concluding":[97],"remark":[98],"made":[100],"from":[101],"perspectives":[103],"authors.":[106],"1":[107]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2016-06-24T00:00:00"}