{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T16:30:33Z","timestamp":1783096233533,"version":"3.54.6"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,5,30]]},"DOI":"10.1109\/icra48506.2021.9560748","type":"proceedings-article","created":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:28:35Z","timestamp":1634689715000},"page":"8699-8705","source":"Crossref","is-referenced-by-count":104,"title":["Distributed Heuristic Multi-Agent Path Finding with Communication"],"prefix":"10.1109","author":[{"given":"Ziyuan","family":"Ma","sequence":"first","affiliation":[{"name":"Simon Fraser University,School of Computing Science,Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yudong","family":"Luo","sequence":"additional","affiliation":[{"name":"Simon Fraser University,School of Computing Science,Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hang","family":"Ma","sequence":"additional","affiliation":[{"name":"Simon Fraser University,School of Computing Science,Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Emergence of locomotion behaviours in rich environments","author":"heess","year":"2017"},{"key":"ref38","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2016","journal-title":"Proc of the International Conference on Machine Learning (ICML)"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2994035"},{"key":"ref32","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc of the International Conference on Machine Learning (ICML)"},{"key":"ref31","first-page":"2154","article-title":"Value iteration networks","author":"tamar","year":"2016","journal-title":"Proc Advances in Neural Information Processing Systems (NIPS’16)"},{"key":"ref30","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"Proc Advances in Neural Information Processing Systems (NIPS’17)"},{"key":"ref37","first-page":"1538","article-title":"Tarmac: Targeted multi-agent communication","author":"das","year":"2019","journal-title":"Proc of the International Conference on Machine Learning (ICML)"},{"key":"ref36","article-title":"Graph convolutional reinforcement learning","author":"jiang","year":"2020","journal-title":"Proc International Conference on Learning Representations (ICLR’20)"},{"key":"ref35","first-page":"2137","article-title":"Learning to communicate with deep multi-agent reinforcement learning","author":"foerster","year":"2016","journal-title":"Proc Advances in Neural Information Processing Systems (NIPS’16)"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3026638"},{"key":"ref10","first-page":"810","article-title":"Efficient sat approach to multi-agent path finding under the sum of costs objective","author":"surynek","year":"2016","journal-title":"Proceedings of European conference on artificial intelligence"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1613\/jair.4171"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2014.11.001"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2014.11.006"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/63"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989037"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461113"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2903261"},{"key":"ref18","article-title":"Mapper: Multi-agent path planning with evolutionary reinforcement learning in mixed dynamic environments","author":"liu","year":"2020","journal-title":"Proc of the IEEE International Conference on Intelligent Robots and Systems (IROS’20)"},{"key":"ref19","article-title":"Distributed prioritized experience replay","author":"horgan","year":"2018","journal-title":"Proc International Conference on Learning Representations (ICLR’18)"},{"key":"ref28","first-page":"4295","article-title":"Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning","author":"rashid","year":"2018","journal-title":"Proc of the International Conference on Machine Learning (ICML)"},{"key":"ref4","article-title":"Planning, scheduling and monitoring for airport surface operations","author":"morris","year":"2016","journal-title":"Proc AAAI-16 Workshop Planning for Hybrid Systems"},{"key":"ref27","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","author":"sunehag","year":"2018","journal-title":"AAMAS"},{"key":"ref3","article-title":"Cobots: Robust symbiotic autonomous mobile service robots","author":"veloso","year":"2015","journal-title":"Proc International Joint Conference on Artificial Intelligence (IJCAI’15)"},{"key":"ref6","first-page":"270","article-title":"Feasibility study: Moving non-homogeneous teams in congested video game environments","author":"ma","year":"2017","journal-title":"Proc AAAI Conf Artif Intell Interactive Digit Entertain"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11794","article-title":"Counterfactual multi-agent policy gradients","author":"foerster","year":"2018","journal-title":"Proc AAAI Conference on Artificial Intelligence (AAAI’18)"},{"key":"ref5","first-page":"117","article-title":"Cooperative pathfinding","author":"silver","year":"2005","journal-title":"Proc AAAI Conf Artif Intell Interactive Digit Entertain"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2715406"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v27i1.8541","article-title":"Structure and intractability of optimal multirobot path planning on graphs","author":"yu","year":"2013","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref2","first-page":"9","article-title":"Coordinating hundreds of cooperative, autonomous vehicles in warehouses","volume":"29","author":"wurman","year":"2008","journal-title":"AI Magazine"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6631084"},{"key":"ref1","first-page":"151","article-title":"Multi-agent pathfinding: Definitions, variants, and benchmarks","author":"stern","year":"2019","journal-title":"Symposium on Combinatorial Search"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref21","first-page":"157","article-title":"Markov games as a framework for multi-agent reinforcement learning","author":"littman","year":"1994","journal-title":"Proc of the International Conference on Machine Learning (ICML)"},{"key":"ref24","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"}],"event":{"name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","location":"Xi'an, China","start":{"date-parts":[[2021,5,30]]},"end":{"date-parts":[[2021,6,5]]}},"container-title":["2021 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9560720\/9560666\/09560748.pdf?arnumber=9560748","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,12]],"date-time":"2023-01-12T22:50:11Z","timestamp":1673563811000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9560748\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,30]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/icra48506.2021.9560748","relation":{},"subject":[],"published":{"date-parts":[[2021,5,30]]}}}