{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:19:45Z","timestamp":1776885585818,"version":"3.51.2"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NSERC Collaborative Research and Development"},{"DOI":"10.13039\/501100001804","name":"Canada Research Chairs","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001804","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2023,1]]},"DOI":"10.1109\/lra.2022.3224667","type":"journal-article","created":{"date-parts":[[2022,11,24]],"date-time":"2022-11-24T21:31:50Z","timestamp":1669325510000},"page":"272-279","source":"Crossref","is-referenced-by-count":50,"title":["Deep Reinforcement Learning for Decentralized Multi-Robot Exploration With Macro Actions"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3918-2692","authenticated-orcid":false,"given":"Aaron Hao","family":"Tan","sequence":"first","affiliation":[{"name":"Autonomous Systems and Biomechatronics Laboratory (ASBLab), Department of Mechanical and Industrial Engineering, University of Toronto, Toronto, ON, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4566-6466","authenticated-orcid":false,"given":"Federico Pizarro","family":"Bejarano","sequence":"additional","affiliation":[{"name":"Autonomous Systems and Biomechatronics Laboratory (ASBLab), Department of Mechanical and Industrial Engineering, University of Toronto, Toronto, ON, Canada"}]},{"given":"Yuhan","family":"Zhu","sequence":"additional","affiliation":[{"name":"Autonomous Systems and Biomechatronics Laboratory (ASBLab), Department of Mechanical and Industrial Engineering, University of Toronto, Toronto, ON, Canada"}]},{"given":"Richard","family":"Ren","sequence":"additional","affiliation":[{"name":"Autonomous Systems and Biomechatronics Laboratory (ASBLab), Department of Mechanical and Industrial Engineering, University of Toronto, Toronto, ON, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7080-6857","authenticated-orcid":false,"given":"Goldie","family":"Nejat","sequence":"additional","affiliation":[{"name":"Autonomous Systems and Biomechatronics Laboratory (ASBLab), Department of Mechanical and Industrial Engineering, University of Toronto, Toronto, ON, Canada"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21831"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30301-5"},{"key":"ref33","first-page":"29","article-title":"Deep recurrent q-learning for partially observable MDPs","author":"hausknecht","year":"2015","journal-title":"Proc AAAI Fall Symp"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11418"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2004.839232"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/280765.280773"},{"key":"ref36","first-page":"313","article-title":"Multi-robot path planning with the spatio-temporal A* algorithm and its variants","author":"wang","year":"2011","journal-title":"Proc 1st Int Conf Autonomous Agents Multiagent Syst"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-07455-9_3"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3093551"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ECMR.2013.6698833"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2891991"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/AGENTS.2019.8929192"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS51040.2020.00032"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3146912"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref16","first-page":"1146","article-title":"Macro-action-based deep multi-agent reinforcement learning","author":"xiao","year":"2020","journal-title":"Proc Conf Robot Learn"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196684"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10472-009-9123-z"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2002.1013690"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21236\/ADA526116"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"929","DOI":"10.1108\/IR-04-2020-0073","article-title":"Review on state-of-the-art dynamic task allocation strategies for multiple-robot systems","volume":"47","author":"seenu","year":"2020","journal-title":"Ind Robot"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33515-0_49"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21597"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/e21030294"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-019-09828-5"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-04239-4_4"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-019-09421-1"},{"key":"ref7","first-page":"2017","article-title":"Coordinated multi-robot exploration under communication constraints using decentralized Markov decision processes","author":"matignon","year":"2012","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139350"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SSRR.2018.8468643"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2000.844100"},{"key":"ref20","first-page":"99","article-title":"Multi-robot decentralized exploration using a trade-based approach","author":"yan","year":"2011","journal-title":"Proc Int Conf Inform Control Automat Robot"},{"key":"ref22","first-page":"505","article-title":"Energy-efficient mobile robot exploration","author":"mei","year":"2006","journal-title":"Proc IEEE Int Conf Robot Automat"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"945","DOI":"10.1016\/j.robot.2006.06.003","article-title":"Distributed multi-robot coordination for area exploration and mapping","volume":"54","author":"fox","year":"2006","journal-title":"Robot Auton Syst"},{"key":"ref24","first-page":"852","article-title":"Coordination for multi-robot exploration and mapping","author":"simmons","year":"2000","journal-title":"Proc Conf Innov Appl Artif Intell"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509993"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2006.1641950"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2851613.2851706"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9963768\/09963690.pdf?arnumber=9963690","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:18:05Z","timestamp":1672082285000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9963690\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1]]},"references-count":40,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/lra.2022.3224667","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1]]}}}