{"id":"https://openalex.org/W4410087040","doi":"https://doi.org/10.1109/ccnc54725.2025.10976107","title":"MARS: Multi-Agent Deep Reinforcement Learning for Complex Environment Exploration","display_name":"MARS: Multi-Agent Deep Reinforcement Learning for Complex Environment Exploration","publication_year":2025,"publication_date":"2025-01-10","ids":{"openalex":"https://openalex.org/W4410087040","doi":"https://doi.org/10.1109/ccnc54725.2025.10976107"},"language":"en","primary_location":{"id":"doi:10.1109/ccnc54725.2025.10976107","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccnc54725.2025.10976107","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 22nd Consumer Communications &amp;amp; Networking Conference (CCNC)","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/A5117435661","display_name":"Francesco Gervino","orcid":null},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Polytechnic University of Turin","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Francesco Gervino","raw_affiliation_strings":["Politecnico di Torino,Department of Control and Computer Engineering,Italy"],"affiliations":[{"raw_affiliation_string":"Politecnico di Torino,Department of Control and Computer Engineering,Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065713459","display_name":"Andrea Eirale","orcid":"https://orcid.org/0000-0003-4172-0365"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Polytechnic University of Turin","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrea Eirale","raw_affiliation_strings":["Politecnico di Torino,Department of Electronics and Telecommunications,Italy"],"affiliations":[{"raw_affiliation_string":"Politecnico di Torino,Department of Electronics and Telecommunications,Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009477620","display_name":"Marcello Chiaberge","orcid":"https://orcid.org/0000-0002-1921-0126"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Polytechnic University of Turin","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marcello Chiaberge","raw_affiliation_strings":["Politecnico di Torino,Department of Electronics and Telecommunications,Italy"],"affiliations":[{"raw_affiliation_string":"Politecnico di Torino,Department of Electronics and Telecommunications,Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011246061","display_name":"Alessio Sacco","orcid":"https://orcid.org/0000-0003-2835-5455"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Polytechnic University of Turin","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessio Sacco","raw_affiliation_strings":["Politecnico di Torino,Department of Control and Computer Engineering,Italy"],"affiliations":[{"raw_affiliation_string":"Politecnico di Torino,Department of Control and Computer Engineering,Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010269472","display_name":"Guido Marchetto","orcid":"https://orcid.org/0000-0003-3588-9367"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Polytechnic University of Turin","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Guido Marchetto","raw_affiliation_strings":["Politecnico di Torino,Department of Control and Computer Engineering,Italy"],"affiliations":[{"raw_affiliation_string":"Politecnico di Torino,Department of Control and Computer Engineering,Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023714356","display_name":"Claudio Casetti","orcid":"https://orcid.org/0000-0002-9507-8526"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Polytechnic University of Turin","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Claudio Casetti","raw_affiliation_strings":["Politecnico di Torino,Department of Control and Computer Engineering,Italy"],"affiliations":[{"raw_affiliation_string":"Politecnico di Torino,Department of Control and Computer Engineering,Italy","institution_ids":["https://openalex.org/I177477856"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5117435661"],"corresponding_institution_ids":["https://openalex.org/I177477856"],"apc_list":null,"apc_paid":null,"fwci":2.8414,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.90595884,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5533999800682068,"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":0.5533999800682068,"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/mars-exploration-program","display_name":"Mars Exploration Program","score":0.8365665674209595},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8196133375167847},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6671463847160339},{"id":"https://openalex.org/keywords/astrobiology","display_name":"Astrobiology","score":0.5403855443000793},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4623279571533203},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.45643460750579834},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.42274898290634155},{"id":"https://openalex.org/keywords/exploration-of-mars","display_name":"Exploration of Mars","score":0.4194726049900055},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16784217953681946},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0770818293094635}],"concepts":[{"id":"https://openalex.org/C83260615","wikidata":"https://www.wikidata.org/wiki/Q6773121","display_name":"Mars Exploration Program","level":2,"score":0.8365665674209595},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8196133375167847},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6671463847160339},{"id":"https://openalex.org/C87355193","wikidata":"https://www.wikidata.org/wiki/Q411","display_name":"Astrobiology","level":1,"score":0.5403855443000793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4623279571533203},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.45643460750579834},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.42274898290634155},{"id":"https://openalex.org/C68702407","wikidata":"https://www.wikidata.org/wiki/Q716774","display_name":"Exploration of Mars","level":3,"score":0.4194726049900055},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16784217953681946},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0770818293094635},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ccnc54725.2025.10976107","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccnc54725.2025.10976107","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 22nd Consumer Communications &amp;amp; Networking Conference (CCNC)","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":21,"referenced_works":["https://openalex.org/W1903029394","https://openalex.org/W2038396847","https://openalex.org/W2080823437","https://openalex.org/W2107667896","https://openalex.org/W2172103629","https://openalex.org/W2336416123","https://openalex.org/W2563670399","https://openalex.org/W2962887844","https://openalex.org/W2963019567","https://openalex.org/W2966477753","https://openalex.org/W3133205111","https://openalex.org/W3154552531","https://openalex.org/W4214717370","https://openalex.org/W4312742678","https://openalex.org/W4386260462","https://openalex.org/W6677067356","https://openalex.org/W6682324061","https://openalex.org/W6692846177","https://openalex.org/W6731334075","https://openalex.org/W6744643855","https://openalex.org/W6746700414"],"related_works":["https://openalex.org/W1545817325","https://openalex.org/W1520489124","https://openalex.org/W3015786634","https://openalex.org/W2999762813","https://openalex.org/W3085248812","https://openalex.org/W2276798502","https://openalex.org/W774754512","https://openalex.org/W750104118","https://openalex.org/W2995460269","https://openalex.org/W770322104"],"abstract_inverted_index":{"Autonomous":[0],"exploration":[1,97],"of":[2,35,92,98,148,151],"complex,":[3],"unknown":[4,100],"environments":[5],"is":[6,124,176,188],"a":[7,23,27,86,127,135,149,177,185,202,209,213,218],"cutting-edge":[8],"task":[9,40],"not":[10],"entirely":[11],"solved":[12],"by":[13],"the":[14,31,33,48,58,96,107,110,152,158,164,170,182,193],"scientific":[15],"community.":[16],"When":[17],"an":[18,64],"agent":[19,142,216],"needs":[20],"to":[21,56,71,94,145,168,208],"explore":[22],"maze":[24],"without":[25],"any":[26],"priori":[28],"information":[29],"about":[30],"environment,":[32],"lack":[34],"proper":[36],"destinations":[37],"and":[38,75,118,132,162,217],"explicit":[39],"objectives":[41],"make":[42,106],"traditional":[43],"navigation":[44,166,183],"policies":[45],"inappropriate.":[46],"While":[47],"literature":[49],"presents":[50],"some":[51],"sporadic":[52],"deterministic":[53,178,211,220],"systems":[54],"able":[55],"face":[57],"tasks,":[59],"learning":[60],"approaches":[61],"still":[62],"need":[63],"adequate":[65],"investigation":[66],"which":[67,222],"could":[68],"prove":[69],"them":[70],"be":[72],"more":[73],"suitable":[74],"versatile":[76],"for":[77],"this":[78,81],"purpose.":[79],"In":[80],"paper,":[82],"we":[83],"present":[84],"MARS,":[85],"path":[87],"planner":[88,123,175],"that":[89,180],"exploits":[90,113],"swarms":[91],"robots":[93,191],"optimize":[95],"complex":[99],"environments,":[101],"such":[102],"as":[103,126,134],"mazes.":[104],"To":[105],"solution":[108,187],"scalable,":[109],"proposed":[111],"method":[112],"two":[114],"cooperating":[115],"modules:":[116],"local":[117,122,171,186],"global":[119,153,174],"planners.":[120],"The":[121,173,190,227],"modeled":[125],"Markov":[128],"Decision":[129],"Process":[130],"(MDP)":[131],"trained":[133],"Reinforcement":[136],"Learning":[137],"(RL)":[138],"multi-agent":[139],"system.":[140],"Each":[141],"has":[143],"access":[144],"image":[146],"representations":[147],"section":[150,195],"map,":[154],"always":[155],"centered":[156],"in":[157,201,236],"robot":[159],"reference":[160],"frame,":[161],"decides":[163],"next":[165],"goal":[167],"complete":[169],"exploration.":[172],"system":[179],"recovers":[181],"when":[184,198],"unavailable.":[189],"share":[192],"explored":[194],"with":[196],"peers":[197],"they":[199],"meet":[200],"rendez-vous.":[203],"We":[204],"compared":[205],"our":[206],"approach":[207,221],"single":[210,214],"agent,":[212],"RL":[215],"close-to-optimal":[219],"deploys":[223],"five":[224],"greedy":[225],"agents.":[226],"simulation":[228],"results":[229],"demonstrate":[230],"MARS'":[231],"efficiency,":[232],"reaching":[233],"near-optimal":[234],"levels":[235],"significantly":[237],"less":[238],"time.":[239]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
