{"id":"https://openalex.org/W3013941204","doi":"https://doi.org/10.1109/rcar47638.2019.9043928","title":"Multi-agent Reinforcement Learning with Biased Experience Sharing in Swarm-robotics Domain","display_name":"Multi-agent Reinforcement Learning with Biased Experience Sharing in Swarm-robotics Domain","publication_year":2019,"publication_date":"2019-08-01","ids":{"openalex":"https://openalex.org/W3013941204","doi":"https://doi.org/10.1109/rcar47638.2019.9043928","mag":"3013941204"},"language":"en","primary_location":{"id":"doi:10.1109/rcar47638.2019.9043928","is_oa":false,"landing_page_url":"https://doi.org/10.1109/rcar47638.2019.9043928","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Real-time Computing and Robotics (RCAR)","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/A5021284542","display_name":"Jun Wu","orcid":"https://orcid.org/0000-0002-1388-7451"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jun Wu","raw_affiliation_strings":["College of Aerospace Science and Engineering, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Aerospace Science and Engineering, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065080432","display_name":"Caizhi Fan","orcid":"https://orcid.org/0000-0002-3470-3826"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Caizhi Fan","raw_affiliation_strings":["College of Aerospace Science and Engineering, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Aerospace Science and Engineering, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102058575","display_name":"Guofu Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guofu Wu","raw_affiliation_strings":["College of Aerospace Science and Engineering, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Aerospace Science and Engineering, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5021284542"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.14,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.60758075,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"243","last_page":"247"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9990000128746033,"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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9842000007629395,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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":0.8478164672851562},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7039315700531006},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6855098009109497},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.6318532228469849},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5696924924850464},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.562166154384613},{"id":"https://openalex.org/keywords/swarm-robotics","display_name":"Swarm robotics","score":0.5581781268119812},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.4902932941913605},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.48548200726509094},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4774523377418518},{"id":"https://openalex.org/keywords/knowledge-sharing","display_name":"Knowledge sharing","score":0.44180917739868164},{"id":"https://openalex.org/keywords/swarm-behaviour","display_name":"Swarm behaviour","score":0.4275134205818176},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.21803036332130432},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.10786336660385132}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8478164672851562},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7039315700531006},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6855098009109497},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.6318532228469849},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5696924924850464},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.562166154384613},{"id":"https://openalex.org/C169337768","wikidata":"https://www.wikidata.org/wiki/Q2446723","display_name":"Swarm robotics","level":3,"score":0.5581781268119812},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.4902932941913605},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.48548200726509094},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4774523377418518},{"id":"https://openalex.org/C2776604539","wikidata":"https://www.wikidata.org/wiki/Q6423395","display_name":"Knowledge sharing","level":2,"score":0.44180917739868164},{"id":"https://openalex.org/C181335050","wikidata":"https://www.wikidata.org/wiki/Q14915018","display_name":"Swarm behaviour","level":2,"score":0.4275134205818176},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.21803036332130432},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.10786336660385132},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/rcar47638.2019.9043928","is_oa":false,"landing_page_url":"https://doi.org/10.1109/rcar47638.2019.9043928","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Real-time Computing and Robotics (RCAR)","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":9,"referenced_works":["https://openalex.org/W1507591516","https://openalex.org/W1586180972","https://openalex.org/W2014971961","https://openalex.org/W2058412232","https://openalex.org/W2136480330","https://openalex.org/W2145503167","https://openalex.org/W2773499228","https://openalex.org/W2898916015","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W1871202614","https://openalex.org/W4233987368","https://openalex.org/W1988876749","https://openalex.org/W65954170","https://openalex.org/W2518382144","https://openalex.org/W2350154411","https://openalex.org/W4229451618","https://openalex.org/W617387166","https://openalex.org/W2787547275","https://openalex.org/W1966857494"],"abstract_inverted_index":{"Reinforcement":[0,75],"learning":[1,13,38,52,61,83,142],"has":[2,17],"been":[3],"widely":[4],"applied":[5,99],"to":[6,47,81],"solve":[7],"a":[8,70,126,133,140],"diverse":[9],"set":[10],"of":[11,31],"robot":[12],"tasks.":[14],"Experience":[15],"sharing":[16,128],"become":[18],"an":[19],"important":[20],"technique":[21],"for":[22,35,59],"collaborative":[23,101],"multi-robot":[24,60,135],"systems":[25],"in":[26,100],"non-deterministic":[27],"environments.":[28],"However,":[29],"one":[30],"the":[32,41,87],"main":[33],"problems":[34],"multi-agent":[36],"reinforcement":[37],"(MARL)":[39],"is":[40,56,79,119],"large":[42],"state-action":[43],"space,":[44],"which":[45,107],"leads":[46],"low":[48],"convergence":[49,143],"and":[50,65,112],"even":[51],"failures.":[53],"This":[54],"problem":[55],"especially":[57],"true":[58],"with":[62,91,103,125],"limited":[63,109],"communication":[64,110],"mobility.":[66],"In":[67],"this":[68],"paper,":[69],"Bilateral":[71],"Biased":[72],"Neighbors-Sharing":[73],"Cooperative":[74],"Learning":[76],"(BBNS-CRL)":[77],"method":[78,96],"presented":[80],"accelerate":[82],"process":[84],"by":[85,147],"integrating":[86],"neighboring":[88,114],"robots'":[89],"knowledge":[90],"local":[92],"knowledge.":[93],"The":[94,116],"BBNS-CRL":[95,149],"can":[97,144],"be":[98,145],"task":[102,137],"multiple":[104],"homogeneous":[105],"robots,":[106],"have":[108],"distance":[111],"dynamic":[113],"relationship.":[115],"value":[117],"function":[118],"shared":[120],"between":[121],"two":[122],"adjacent":[123],"robots":[124],"biased":[127],"method.":[129,150],"Simulation":[130],"results":[131],"on":[132],"cooperative":[134],"foraging":[136],"show":[138],"that":[139],"better":[141],"achieved":[146],"adopting":[148]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}