{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T22:24:47Z","timestamp":1777501487721,"version":"3.51.4"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"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","award":["RGPIN2020-06540"],"award-info":[{"award-number":["RGPIN2020-06540"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CFI JELF"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2023,8]]},"DOI":"10.1109\/lra.2023.3292004","type":"journal-article","created":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T17:40:35Z","timestamp":1688492435000},"page":"5100-5107","source":"Crossref","is-referenced-by-count":40,"title":["SACHA: Soft Actor-Critic With Heuristic-Based Attention for Partially Observable Multi-Agent Path Finding"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-3964-1426","authenticated-orcid":false,"given":"Qiushi","family":"Lin","sequence":"first","affiliation":[{"name":"School of Computing Science, Simon Fraser University, Burnaby, BC, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0602-0999","authenticated-orcid":false,"given":"Hang","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Computing Science, Simon Fraser University, Burnaby, BC, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340876"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i13.17344"},{"key":"ref15","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2014.11.001"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"1455","DOI":"10.1109\/LRA.2021.3139145","article-title":"Learning selective communication for multi-agent path finding","volume":"7","author":"ma","year":"2022","journal-title":"IEEE Robot Automat Lett"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017643"},{"key":"ref2","first-page":"9","article-title":"Coordinating hundreds of cooperative, autonomous vehicles in warehouses","volume":"29","author":"wurman","year":"2008","journal-title":"AI Mag"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/socs.v10i1.18510"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6095022"},{"key":"ref19","first-page":"1","article-title":"A review of cooperative multi-agent deep reinforcement learning","volume":"53","author":"oroojlooy","year":"2022","journal-title":"Appl Intell"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2014.11.006"},{"key":"ref23","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","author":"iqbal","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref26","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc NeurIPS"},{"key":"ref25","first-page":"13550","article-title":"Heuristic-guided reinforcement learning","author":"cheng","year":"0","journal-title":"Proc NeurIPS"},{"key":"ref20","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"lowe","year":"0","journal-title":"Proc NeurIPS"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref21","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015"},{"key":"ref28","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref27","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2016"},{"key":"ref29","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"0","journal-title":"Proc NeurIPS"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2903261"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2715406"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560748"},{"key":"ref4","first-page":"608","article-title":"Planning, scheduling and monitoring for airport surface operations","author":"morris","year":"0","journal-title":"Proc AAAI Workshops"},{"key":"ref3","first-page":"4423","article-title":"Cobots: Robust symbiotic autonomous mobile service robots","author":"veloso","year":"0","journal-title":"Proc 24th Int Joint Conf Artif Intell"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v27i1.8541"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICIInfS.2012.6304778"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/10153452\/10172216.pdf?arnumber=10172216","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T18:24:59Z","timestamp":1690914299000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10172216\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8]]},"references-count":32,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/lra.2023.3292004","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8]]}}}