{"id":"https://openalex.org/W4289829044","doi":"https://doi.org/10.1109/med54222.2022.9837168","title":"Multi-agent Exploration with Reinforcement Learning","display_name":"Multi-agent Exploration with Reinforcement Learning","publication_year":2022,"publication_date":"2022-06-28","ids":{"openalex":"https://openalex.org/W4289829044","doi":"https://doi.org/10.1109/med54222.2022.9837168"},"language":"en","primary_location":{"id":"doi:10.1109/med54222.2022.9837168","is_oa":false,"landing_page_url":"https://doi.org/10.1109/med54222.2022.9837168","pdf_url":null,"source":{"id":"https://openalex.org/S4363608151","display_name":"2022 30th Mediterranean Conference on Control and Automation (MED)","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 30th Mediterranean Conference on Control and Automation (MED)","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/A5062158943","display_name":"Alkis Sygkounas","orcid":null},"institutions":[{"id":"https://openalex.org/I174878644","display_name":"University of Patras","ror":"https://ror.org/017wvtq80","country_code":"GR","type":"education","lineage":["https://openalex.org/I174878644"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Alkis Sygkounas","raw_affiliation_strings":["University of Patras,Department of Electrical and Computer Engineering,Greece","Department of Electrical and Computer Engineering, University of Patras, Greece"],"affiliations":[{"raw_affiliation_string":"University of Patras,Department of Electrical and Computer Engineering,Greece","institution_ids":["https://openalex.org/I174878644"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Patras, Greece","institution_ids":["https://openalex.org/I174878644"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031414845","display_name":"Dimitris Tsipianitis","orcid":null},"institutions":[{"id":"https://openalex.org/I174878644","display_name":"University of Patras","ror":"https://ror.org/017wvtq80","country_code":"GR","type":"education","lineage":["https://openalex.org/I174878644"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Dimitris Tsipianitis","raw_affiliation_strings":["University of Patras,Department of Electrical and Computer Engineering,Greece","Department of Electrical and Computer Engineering, University of Patras, Greece"],"affiliations":[{"raw_affiliation_string":"University of Patras,Department of Electrical and Computer Engineering,Greece","institution_ids":["https://openalex.org/I174878644"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Patras, Greece","institution_ids":["https://openalex.org/I174878644"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064878830","display_name":"George Nikolakopoulos","orcid":"https://orcid.org/0000-0003-0126-1897"},"institutions":[{"id":"https://openalex.org/I190632392","display_name":"Lule\u00e5 University of Technology","ror":"https://ror.org/016st3p78","country_code":"SE","type":"education","lineage":["https://openalex.org/I190632392"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"George Nikolakopoulos","raw_affiliation_strings":["Lulea University of Technology,Department of Robotics and AI,Sweden","Department of Robotics and AI, Lulea University of Technology, Sweden"],"affiliations":[{"raw_affiliation_string":"Lulea University of Technology,Department of Robotics and AI,Sweden","institution_ids":["https://openalex.org/I190632392"]},{"raw_affiliation_string":"Department of Robotics and AI, Lulea University of Technology, Sweden","institution_ids":["https://openalex.org/I190632392"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020695725","display_name":"Charalampos P. Bechlioulis","orcid":"https://orcid.org/0000-0001-9850-2540"},"institutions":[{"id":"https://openalex.org/I174878644","display_name":"University of Patras","ror":"https://ror.org/017wvtq80","country_code":"GR","type":"education","lineage":["https://openalex.org/I174878644"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Charalampos P. Bechlioulis","raw_affiliation_strings":["University of Patras,Department of Electrical and Computer Engineering,Greece","Department of Electrical and Computer Engineering, University of Patras, Greece"],"affiliations":[{"raw_affiliation_string":"University of Patras,Department of Electrical and Computer Engineering,Greece","institution_ids":["https://openalex.org/I174878644"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Patras, Greece","institution_ids":["https://openalex.org/I174878644"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5062158943"],"corresponding_institution_ids":["https://openalex.org/I174878644"],"apc_list":null,"apc_paid":null,"fwci":0.6243,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.67208964,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"630","last_page":"635"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9939000010490417,"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":0.9939000010490417,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9811000227928162,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9692000150680542,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7793582677841187},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7614454627037048},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6430887579917908},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6030817627906799},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5968019962310791},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5904642343521118},{"id":"https://openalex.org/keywords/plan","display_name":"Plan (archaeology)","score":0.44157683849334717},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39439821243286133}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7793582677841187},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7614454627037048},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6430887579917908},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6030817627906799},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5968019962310791},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5904642343521118},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.44157683849334717},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39439821243286133},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/med54222.2022.9837168","is_oa":false,"landing_page_url":"https://doi.org/10.1109/med54222.2022.9837168","pdf_url":null,"source":{"id":"https://openalex.org/S4363608151","display_name":"2022 30th Mediterranean Conference on Control and Automation (MED)","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 30th Mediterranean Conference on Control and Automation (MED)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320310968","display_name":"University of Patras","ror":"https://ror.org/017wvtq80"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2586732548","https://openalex.org/W3049728571"],"abstract_inverted_index":{"Modern":[0],"robots":[1,28],"are":[2,13,156],"used":[3,157],"in":[4,38,184],"many":[5],"exploration,":[6],"search":[7],"and":[8,19,58,83,101,112,215],"rescue":[9,24],"applications":[10],"nowadays.":[11],"They":[12],"essentially":[14],"coordinated":[15],"by":[16,162],"human":[17],"operators":[18],"collaborate":[20],"with":[21,34,69,167],"inspection":[22],"or":[23],"teams.":[25],"Over":[26],"time,":[27],"(agents)":[29],"have":[30,91,107],"become":[31],"more":[32,35],"sophisticated":[33],"autonomy,":[36],"operating":[37],"complex":[39],"environments.":[40,61],"Therefore,":[41],"the":[42,77,97,102,114,126,132,147,179,202,205],"purpose":[43],"of":[44,149,174,178,204,213,218],"this":[45],"paper":[46],"is":[47,182,207],"to":[48,75,110,145,198],"present":[49],"an":[50,163],"approach":[51],"for":[52,56,79,158,192,209],"autonomous":[53],"multi-agent":[54],"coordination":[55],"exploring":[57],"covering":[59],"unknown":[60,180],"The":[62,176],"method":[63],"we":[64,90,135],"suggest":[65],"combines":[66],"reinforcement":[67],"learning":[68],"multiple":[70,190],"neural":[71,99,154,165,219],"networks":[72,155],"(Deep":[73],"Learning)":[74],"plan":[76],"path":[78],"each":[80,150],"agent":[81],"separately":[82],"achieve":[84],"collaborative":[85],"behavior":[86],"amongst":[87],"them.":[88,175],"Specifically,":[89],"applied":[92],"two":[93,153],"recent":[94],"techniques,":[95],"namely":[96],"target":[98],"network":[100,166],"prioritized":[103],"experience":[104],"replay,":[105],"which":[106],"been":[108],"proven":[109],"stabilize":[111],"accelerate":[113],"training":[115],"process.":[116],"Agents":[117],"should":[118],"also":[119],"avoid":[120],"obstacles":[121],"(walls,":[122],"objects,":[123],"etc.)":[124],"throughout":[125],"exploration":[127,177,206],"without":[128],"prior":[129],"information/knowledge":[130],"about":[131],"environment;":[133],"thus":[134],"use":[136],"only":[137],"local":[138],"information":[139],"available":[140],"at":[141],"any":[142],"time":[143],"instant":[144],"make":[146],"decision":[148],"agent.":[151],"Furthermore,":[152],"generating":[159],"actions,":[160],"accompanied":[161],"extra":[164],"a":[168,185,210],"switching":[169],"logic":[170],"that":[171],"chooses":[172],"one":[173],"environment":[181],"conducted":[183],"two-dimensional":[186],"model":[187],"(2D)":[188],"using":[189],"agents":[191,214],"various":[193,216],"maps,":[194],"ranging":[195],"from":[196],"small":[197],"large":[199],"size.":[200],"Finally,":[201],"efficiency":[203],"investigated":[208],"different":[211],"number":[212],"types":[217],"networks.":[220]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}