{"id":"https://openalex.org/W2996134258","doi":"https://doi.org/10.1109/agents.2019.8929192","title":"End-to-end Deep Reinforcement Learning for Multi-agent Collaborative Exploration","display_name":"End-to-end Deep Reinforcement Learning for Multi-agent Collaborative Exploration","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2996134258","doi":"https://doi.org/10.1109/agents.2019.8929192","mag":"2996134258"},"language":"en","primary_location":{"id":"doi:10.1109/agents.2019.8929192","is_oa":false,"landing_page_url":"https://doi.org/10.1109/agents.2019.8929192","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 Agents (ICA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ink.library.smu.edu.sg/sis_research/6170","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104078124","display_name":"Zichen Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Zichen Chen","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062773086","display_name":"Budhitama Subagdja","orcid":"https://orcid.org/0000-0001-9774-0264"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Budhitama Subagdja","raw_affiliation_strings":["ST Engineering-NTU Corporate Laboratory, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ST Engineering-NTU Corporate Laboratory, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004167801","display_name":"Ah\u2010Hwee Tan","orcid":"https://orcid.org/0000-0003-0378-4069"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ah-Hwee Tan","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5104078124"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":0.7259,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.79599093,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"99","last_page":"102"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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":0.9991000294685364,"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":0.994700014591217,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9865000247955322,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8948302268981934},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.772463321685791},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7080903649330139},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5739675760269165},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5506526827812195},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.520571768283844},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.48463210463523865},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4490925073623657},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.33050623536109924}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8948302268981934},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.772463321685791},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7080903649330139},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5739675760269165},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5506526827812195},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.520571768283844},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48463210463523865},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4490925073623657},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33050623536109924},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/agents.2019.8929192","is_oa":false,"landing_page_url":"https://doi.org/10.1109/agents.2019.8929192","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 Agents (ICA)","raw_type":"proceedings-article"},{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-7173","is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/sis_research/6170","pdf_url":null,"source":{"id":"https://openalex.org/S4377196871","display_name":"Institutional Knowledge (InK) - Institutional Knowledge at Singapore Management University (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"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":"https://doi.org/10.1109/AGENTS.2019.8929192","raw_type":"Conference Proceeding Article"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/148510","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/148510","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-7173","is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/sis_research/6170","pdf_url":null,"source":{"id":"https://openalex.org/S4377196871","display_name":"Institutional Knowledge (InK) - Institutional Knowledge at Singapore Management University (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"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":"https://doi.org/10.1109/AGENTS.2019.8929192","raw_type":"Conference Proceeding Article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W82838842","https://openalex.org/W188325927","https://openalex.org/W201680239","https://openalex.org/W1522301498","https://openalex.org/W1966213627","https://openalex.org/W2104969271","https://openalex.org/W2117838550","https://openalex.org/W2129853306","https://openalex.org/W2254288984","https://openalex.org/W2296073425","https://openalex.org/W2411321320","https://openalex.org/W2736601468","https://openalex.org/W2751973545","https://openalex.org/W2891234582","https://openalex.org/W2963523627","https://openalex.org/W2963658727","https://openalex.org/W2964121744","https://openalex.org/W6603345786","https://openalex.org/W6607597900","https://openalex.org/W6631190155","https://openalex.org/W6691621831","https://openalex.org/W6741002519"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W4293226380","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W2024136090","https://openalex.org/W1508899372"],"abstract_inverted_index":{"Exploring":[0],"an":[1],"unknown":[2],"environment":[3,65,111],"by":[4],"multiple":[5,16,106],"autonomous":[6],"robots":[7,17],"is":[8],"a":[9,40,67],"major":[10],"challenge":[11],"in":[12],"robotics":[13],"domains.":[14],"As":[15],"are":[18],"assigned":[19],"to":[20,50,60,79,108],"explore":[21,63,109],"different":[22],"locations,":[23],"they":[24],"may":[25],"interfere":[26],"each":[27],"other":[28],"making":[29],"the":[30,54,57,64,97,110,113],"overall":[31],"tasks":[32],"less":[33],"efficient.":[34],"In":[35],"this":[36],"paper,":[37],"we":[38],"present":[39],"new":[41,68],"model":[42,74],"called":[43],"CNN-based":[44],"Multi-agent":[45],"Proximal":[46],"Policy":[47],"Optimization":[48],"(CMAPPO)":[49],"multi-agent":[51],"exploration":[52],"wherein":[53],"agents":[55,107],"learn":[56,101],"effective":[58],"strategy":[59,104],"allocate":[61],"and":[62,86],"using":[66],"deep":[69],"reinforcement":[70,92],"learning":[71],"architecture.":[72],"The":[73],"combines":[75],"convolutional":[76],"neural":[77],"network":[78],"process":[80],"multi-channel":[81],"visual":[82],"inputs,":[83],"curriculum-based":[84],"learning,":[85],"PPO":[87],"algorithm":[88],"for":[89,105],"motivation":[90],"based":[91],"learning.":[93],"Evaluations":[94],"show":[95],"that":[96],"proposed":[98],"method":[99],"can":[100],"more":[102],"efficient":[103],"than":[112],"conventional":[114],"frontier-based":[115],"method.":[116]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-05-02T08:42:23.175194","created_date":"2025-10-10T00:00:00"}