{"id":"https://openalex.org/W3202938653","doi":"https://doi.org/10.1109/lra.2022.3224667","title":"Deep Reinforcement Learning for Decentralized Multi-Robot Exploration With Macro Actions","display_name":"Deep Reinforcement Learning for Decentralized Multi-Robot Exploration With Macro Actions","publication_year":2022,"publication_date":"2022-11-24","ids":{"openalex":"https://openalex.org/W3202938653","doi":"https://doi.org/10.1109/lra.2022.3224667","mag":"3202938653"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2022.3224667","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2022.3224667","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-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/A5068929601","display_name":"Aaron Hao Tan","orcid":"https://orcid.org/0000-0003-3918-2692"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Aaron Hao Tan","raw_affiliation_strings":["Autonomous Systems and Biomechatronics Laboratory (ASBLab), Department of Mechanical and Industrial Engineering, University of Toronto, Toronto, ON, Canada"],"raw_orcid":"https://orcid.org/0000-0003-3918-2692","affiliations":[{"raw_affiliation_string":"Autonomous Systems and Biomechatronics Laboratory (ASBLab), Department of Mechanical and Industrial Engineering, University of Toronto, Toronto, ON, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007539078","display_name":"Federico Pizarro Bejarano","orcid":"https://orcid.org/0000-0003-4566-6466"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Federico Pizarro Bejarano","raw_affiliation_strings":["Autonomous Systems and Biomechatronics Laboratory (ASBLab), Department of Mechanical and Industrial Engineering, University of Toronto, Toronto, ON, Canada"],"raw_orcid":"https://orcid.org/0000-0003-4566-6466","affiliations":[{"raw_affiliation_string":"Autonomous Systems and Biomechatronics Laboratory (ASBLab), Department of Mechanical and Industrial Engineering, University of Toronto, Toronto, ON, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089098757","display_name":"Yuhan Zhu","orcid":"https://orcid.org/0000-0002-0246-3653"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yuhan Zhu","raw_affiliation_strings":["Autonomous Systems and Biomechatronics Laboratory (ASBLab), Department of Mechanical and Industrial Engineering, University of Toronto, Toronto, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Autonomous Systems and Biomechatronics Laboratory (ASBLab), Department of Mechanical and Industrial Engineering, University of Toronto, Toronto, ON, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043150501","display_name":"Richard Ren","orcid":"https://orcid.org/0000-0001-5628-7926"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Richard Ren","raw_affiliation_strings":["Autonomous Systems and Biomechatronics Laboratory (ASBLab), Department of Mechanical and Industrial Engineering, University of Toronto, Toronto, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Autonomous Systems and Biomechatronics Laboratory (ASBLab), Department of Mechanical and Industrial Engineering, University of Toronto, Toronto, ON, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061187299","display_name":"Goldie Nejat","orcid":"https://orcid.org/0000-0002-7080-6857"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Goldie Nejat","raw_affiliation_strings":["Autonomous Systems and Biomechatronics Laboratory (ASBLab), Department of Mechanical and Industrial Engineering, University of Toronto, Toronto, ON, Canada"],"raw_orcid":"https://orcid.org/0000-0002-7080-6857","affiliations":[{"raw_affiliation_string":"Autonomous Systems and Biomechatronics Laboratory (ASBLab), Department of Mechanical and Industrial Engineering, University of Toronto, Toronto, ON, Canada","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5068929601"],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":null,"apc_paid":null,"fwci":5.9654,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.96631916,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"8","issue":"1","first_page":"272","last_page":"279"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9904000163078308,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9898999929428101,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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":0.8011089563369751},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7188153266906738},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7060121297836304},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6701096296310425},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6219407916069031},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.620577335357666},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5774946808815002},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.5545519590377808},{"id":"https://openalex.org/keywords/macro","display_name":"Macro","score":0.48890987038612366},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.43402692675590515},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39129623770713806},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.35794466733932495}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8011089563369751},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7188153266906738},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7060121297836304},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6701096296310425},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6219407916069031},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.620577335357666},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5774946808815002},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.5545519590377808},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.48890987038612366},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.43402692675590515},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39129623770713806},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.35794466733932495},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2022.3224667","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2022.3224667","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320994","display_name":"Canada Research Chairs","ror":"https://ror.org/0517h6h17"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W82838842","https://openalex.org/W193832275","https://openalex.org/W1560270123","https://openalex.org/W1832534480","https://openalex.org/W1933691875","https://openalex.org/W1966213627","https://openalex.org/W1970524896","https://openalex.org/W2031369387","https://openalex.org/W2031597354","https://openalex.org/W2061085501","https://openalex.org/W2062573767","https://openalex.org/W2109910161","https://openalex.org/W2110795172","https://openalex.org/W2113739894","https://openalex.org/W2121092017","https://openalex.org/W2134877736","https://openalex.org/W2135524320","https://openalex.org/W2139338077","https://openalex.org/W2142924305","https://openalex.org/W2145339207","https://openalex.org/W2152475379","https://openalex.org/W2290743114","https://openalex.org/W2396783599","https://openalex.org/W2406617028","https://openalex.org/W2461193511","https://openalex.org/W2495871221","https://openalex.org/W2744979297","https://openalex.org/W2892245714","https://openalex.org/W2898231767","https://openalex.org/W2901739119","https://openalex.org/W2910054127","https://openalex.org/W2912730013","https://openalex.org/W2914661444","https://openalex.org/W2920854821","https://openalex.org/W2924816077","https://openalex.org/W2962938178","https://openalex.org/W2970283989","https://openalex.org/W2981038142","https://openalex.org/W2996134258","https://openalex.org/W3016477472","https://openalex.org/W3031556054","https://openalex.org/W3087771514","https://openalex.org/W3090863380","https://openalex.org/W3096656822","https://openalex.org/W3100789280","https://openalex.org/W3134938521","https://openalex.org/W3176880374","https://openalex.org/W4210356871","https://openalex.org/W4230129068","https://openalex.org/W6638704531","https://openalex.org/W6665964885","https://openalex.org/W6677939520","https://openalex.org/W6680023198","https://openalex.org/W6712348848","https://openalex.org/W6714079524","https://openalex.org/W6775788706"],"related_works":["https://openalex.org/W2030816003","https://openalex.org/W2378211422","https://openalex.org/W2015051472","https://openalex.org/W2168501056","https://openalex.org/W2120009678","https://openalex.org/W2912947802","https://openalex.org/W2037601570","https://openalex.org/W2123856982","https://openalex.org/W3037510552","https://openalex.org/W1530089576"],"abstract_inverted_index":{"Cooperative":[0],"multi-robot":[1,67],"teams":[2],"need":[3,31],"to":[4,7,25,32,59],"be":[5],"able":[6],"explore":[8],"cluttered":[9,73],"and":[10,72,82,86,109,135,144],"unstructured":[11],"environments":[12,123],"while":[13],"dealing":[14],"with":[15,130,132],"communication":[16,64,116],"dropouts":[17,65],"that":[18],"prevent":[19],"them":[20],"from":[21],"exchanging":[22],"local":[23,105],"information":[24],"maintain":[26],"team":[27,77,134],"coordination.":[28],"Therefore,":[29],"robots":[30],"consider":[33],"high-level":[34],"teammate":[35],"intentions":[36],"during":[37,66],"action":[38],"selection.":[39],"In":[40],"this":[41],"letter,":[42],"we":[43],"present":[44],"the":[45,61,142],"first":[46],"Macro":[47],"Action":[48],"Decentralized":[49],"Exploration":[50],"Network":[51],"(MADE-Net)":[52],"using":[53],"multi-agent":[54],"deep":[55],"reinforcement":[56],"learning":[57],"(DRL)":[58],"address":[60],"challenges":[62],"of":[63,97,104,115,146],"exploration":[68,78,110,128],"in":[69,95,121,127],"unseen,":[70],"unstructured,":[71],"environments.":[74],"Simulated":[75],"robot":[76],"experiments":[79,139],"were":[80],"conducted":[81],"compared":[83],"against":[84],"classical":[85],"DRL":[87],"methods":[88,94],"where":[89],"MADE-Net":[90,131],"outperformed":[91],"all":[92],"benchmark":[93],"terms":[96],"computation":[98],"time,":[99],"total":[100],"travel":[101],"distance,":[102],"number":[103],"interactions":[106],"between":[107],"robots,":[108],"rate":[111],"across":[112],"various":[113],"degrees":[114],"dropouts.":[117],"A":[118],"scalability":[119],"study":[120],"3D":[122],"showed":[124],"a":[125],"decrease":[126],"time":[129],"increasing":[133],"environment":[136],"sizes.":[137],"The":[138],"presented":[140],"highlight":[141],"effectiveness":[143],"robustness":[145],"our":[147],"method.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":23},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}