{"id":"https://openalex.org/W4405785046","doi":"https://doi.org/10.1109/iros58592.2024.10801319","title":"D-MARL: A Dynamic Communication-Based Action Space Enhancement for Multi Agent Reinforcement Learning Exploration of Large Scale Unknown Environments","display_name":"D-MARL: A Dynamic Communication-Based Action Space Enhancement for Multi Agent Reinforcement Learning Exploration of Large Scale Unknown Environments","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405785046","doi":"https://doi.org/10.1109/iros58592.2024.10801319"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10801319","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801319","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ltu.diva-portal.org/smash/get/diva2:1914206/FULLTEXT02","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011569148","display_name":"G Calzolari","orcid":null},"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":true,"raw_author_name":"Gabriele Calzolari","raw_affiliation_strings":["Lule&#x00E5; University of Technology,Robotics and AI Group,Department of Computer Science, Electrical and Space Engineering,Sweden"],"affiliations":[{"raw_affiliation_string":"Lule&#x00E5; University of Technology,Robotics and AI Group,Department of Computer Science, Electrical and Space Engineering,Sweden","institution_ids":["https://openalex.org/I190632392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104337143","display_name":"Vidya Sumathy","orcid":null},"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":"Vidya Sumathy","raw_affiliation_strings":["Lule&#x00E5; University of Technology,Robotics and AI Group,Department of Computer Science, Electrical and Space Engineering,Sweden"],"affiliations":[{"raw_affiliation_string":"Lule&#x00E5; University of Technology,Robotics and AI Group,Department of Computer Science, Electrical and Space Engineering,Sweden","institution_ids":["https://openalex.org/I190632392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039277979","display_name":"Christoforos Kanellakis","orcid":"https://orcid.org/0000-0001-8870-6718"},"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":"Christoforos Kanellakis","raw_affiliation_strings":["Lule&#x00E5; University of Technology,Robotics and AI Group,Department of Computer Science, Electrical and Space Engineering,Sweden"],"affiliations":[{"raw_affiliation_string":"Lule&#x00E5; University of Technology,Robotics and AI Group,Department of Computer Science, Electrical and Space Engineering,Sweden","institution_ids":["https://openalex.org/I190632392"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032260126","display_name":"George Nikolakopoulos","orcid":null},"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":["Lule&#x00E5; University of Technology,Robotics and AI Group,Department of Computer Science, Electrical and Space Engineering,Sweden"],"affiliations":[{"raw_affiliation_string":"Lule&#x00E5; University of Technology,Robotics and AI Group,Department of Computer Science, Electrical and Space Engineering,Sweden","institution_ids":["https://openalex.org/I190632392"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5011569148"],"corresponding_institution_ids":["https://openalex.org/I190632392"],"apc_list":null,"apc_paid":null,"fwci":0.7232,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.78174973,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3470","last_page":"3475"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7576000094413757,"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":0.7576000094413757,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.691100001335144,"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":0.8662662506103516},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6784723997116089},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5634623765945435},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5626010894775391},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.48773083090782166},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4827972650527954},{"id":"https://openalex.org/keywords/marl","display_name":"Marl","score":0.43651601672172546},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.42641139030456543},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3040638566017151},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16116932034492493},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08457976579666138},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.08430644869804382},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.07183203101158142}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8662662506103516},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6784723997116089},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5634623765945435},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5626010894775391},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.48773083090782166},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4827972650527954},{"id":"https://openalex.org/C92927620","wikidata":"https://www.wikidata.org/wiki/Q184053","display_name":"Marl","level":3,"score":0.43651601672172546},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.42641139030456543},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3040638566017151},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16116932034492493},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08457976579666138},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.08430644869804382},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07183203101158142},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C109007969","wikidata":"https://www.wikidata.org/wiki/Q749565","display_name":"Structural basin","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iros58592.2024.10801319","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801319","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:DiVA.org:ltu-110753","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:ltu:diva-110753","pdf_url":"https://ltu.diva-portal.org/smash/get/diva2:1914206/FULLTEXT02","source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:DiVA.org:ltu-110753","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:ltu:diva-110753","pdf_url":"https://ltu.diva-portal.org/smash/get/diva2:1914206/FULLTEXT02","source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4405785046.pdf","grobid_xml":"https://content.openalex.org/works/W4405785046.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W82838842","https://openalex.org/W1966213627","https://openalex.org/W2017995647","https://openalex.org/W2113739894","https://openalex.org/W2488801630","https://openalex.org/W2963099939","https://openalex.org/W2967059663","https://openalex.org/W3095315965","https://openalex.org/W3154726838","https://openalex.org/W4210356871","https://openalex.org/W4289829044","https://openalex.org/W4324119510","https://openalex.org/W4392305895","https://openalex.org/W6678073246","https://openalex.org/W6748600884","https://openalex.org/W6771514159","https://openalex.org/W6779878709","https://openalex.org/W6783838878","https://openalex.org/W6840029797","https://openalex.org/W6851389620","https://openalex.org/W6854916296","https://openalex.org/W6861314356"],"related_works":["https://openalex.org/W2126019709","https://openalex.org/W1702901972","https://openalex.org/W4249798507","https://openalex.org/W2069775250","https://openalex.org/W2032294417","https://openalex.org/W2152754392","https://openalex.org/W1989172970","https://openalex.org/W2196316523","https://openalex.org/W1899363654","https://openalex.org/W2507089433"],"abstract_inverted_index":{"In":[0,31,45,66],"this":[1],"article,":[2],"we":[3],"propose":[4],"a":[5],"novel":[6,97],"communication-based":[7],"action":[8],"space":[9],"enhancement":[10],"for":[11],"the":[12,18,60,63,67,77,91,118,141,148,152,163,166],"D-MARL":[13,129],"exploration":[14,122],"algorithm":[15,82],"to":[16,83,87,112,139,161],"improve":[17],"efficiency":[19,114],"of":[20,62,143,151,165],"mapping":[21,119],"an":[22,27],"unknown":[23],"environment,":[24],"represented":[25],"by":[26,75,102],"occupancy":[28],"grid":[29],"map.":[30],"general,":[32],"communication":[33,105],"between":[34],"autonomous":[35,64],"systems":[36],"is":[37,51,73],"crucial":[38],"when":[39],"exploring":[40],"large":[41],"and":[42,53,59,106,115,124],"unstructured":[43],"environments.":[44],"such":[46],"real-world":[47],"scenarios,":[48],"data":[49],"transmission":[50],"limited":[52],"relies":[54],"heavily":[55],"on":[56,132,147],"inter-agent":[57,104],"proximity":[58],"attributes":[61],"platforms.":[65],"proposed":[68,167],"approach,":[69],"each":[70],"agent\u2019s":[71],"policy":[72,80],"optimized":[74],"utilizing":[76],"heterogeneous-agent":[78],"proximal":[79],"optimization":[81],"autonomously":[84],"choose":[85],"whether":[86],"communicate":[88],"or":[89],"explore":[90],"environment.":[92],"To":[93],"accomplish":[94],"this,":[95],"multiple":[96,156],"reward":[98,134,145],"functions":[99,135],"are":[100,159],"formulated":[101],"integrating":[103],"exploration.":[107],"The":[108,128],"investigated":[109],"approach":[110],"aims":[111],"increase":[113],"robustness":[116],"in":[117],"process,":[120],"minimize":[121],"overlap,":[123],"prevent":[125],"agent":[126],"collisions.":[127],"policies":[130],"trained":[131],"different":[133,144],"have":[136],"been":[137],"compared":[138],"understand":[140],"effect":[142],"terms":[146],"collaborative":[149],"attitude":[150],"homogeneous":[153],"agents.":[154],"Finally,":[155],"simulation":[157],"results":[158],"provided":[160],"prove":[162],"efficacy":[164],"scheme.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}
