{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T06:44:46Z","timestamp":1774680286375,"version":"3.50.1"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"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":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tnnls.2023.3303502","type":"journal-article","created":{"date-parts":[[2023,8,31]],"date-time":"2023-08-31T17:38:51Z","timestamp":1693503531000},"page":"17411-17424","source":"Crossref","is-referenced-by-count":15,"title":["When to Switch: Planning and Learning for Partially Observable Multi-Agent Pathfinding"],"prefix":"10.1109","volume":"35","author":[{"given":"Alexey","family":"Skrynnik","sequence":"first","affiliation":[{"name":"Federal Research Center for Computer Science and Control of Russian Academy of Science, Moscow, Russia"}]},{"given":"Anton","family":"Andreychuk","sequence":"additional","affiliation":[{"name":"AIRI, Moscow, Russia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4377-321X","authenticated-orcid":false,"given":"Konstantin","family":"Yakovlev","sequence":"additional","affiliation":[{"name":"Federal Research Center for Computer Science and Control of Russian Academy of Science, Moscow, Russia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9747-3837","authenticated-orcid":false,"given":"Aleksandr I.","family":"Panov","sequence":"additional","affiliation":[{"name":"Federal Research Center for Computer Science and Control of Russian Academy of Science, Moscow, Russia"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/socs.v10i1.18510"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/SFCS.1984.715921"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2016.2593448"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/icaps.v30i1.6663"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017627"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/74"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/6"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017732"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11734"},{"key":"ref10","first-page":"837","article-title":"Lifelong multi-agent path finding for online pickup and delivery tasks","volume-title":"Proc. AAMAS","author":"Ma"},{"key":"ref11","first-page":"757","article-title":"Conflict-based search with optimal task assignment","volume-title":"Proc. AAMAS","author":"Honig"},{"key":"ref12","first-page":"1","article-title":"Sample factory: Egocentric 3D control from pixels at 100000 FPS with asynchronous reinforcement learning","volume-title":"Proc. ICML","author":"Petrenko"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2903261"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2994035"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340876"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3062803"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811643"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2020.3021714"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3232630"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3236361"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v24i1.7564"},{"key":"ref22","first-page":"1263","article-title":"Multi-agent RRT: Sampling-based cooperative pathfinding","volume-title":"Proc. Int. Conf. Auto. Agents Multi-Agent Syst.","author":"\u010c\u00e1p"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3023200"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6095022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2014.11.006"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/BF01840371"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2015.2445780"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ECMR.2019.8870957"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v1i1.18726"},{"key":"ref30","first-page":"55","article-title":"MAPP: A scalable multi-agent path planning algorithm with tractability and completeness guarantees","volume":"42","author":"Wang","year":"2011","journal-title":"J. Artif. Intell. Res."},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1080\/0952813X.2017.1310142"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-19457-3_1"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2656241"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980392"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3026638"},{"key":"ref36","first-page":"2186","article-title":"The StarCraft multi-agent challenge","volume-title":"Proc. Int. Joint Conf. Auto. Agents Multiagent Syst. (AAMAS)","volume":"4","author":"Samvelyan"},{"key":"ref37","first-page":"6846","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. 35th Int. Conf. Mach. Learn. (ICML)","volume":"10","author":"Rashid"},{"key":"ref38","first-page":"12208","article-title":"FACMAC: Factored multi-agent centralised policy gradients","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Peng"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3121546"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3146858"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3262921"},{"key":"ref42","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref43","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2800110"},{"key":"ref45","article-title":"Interpolated policy gradient: Merging on-policy and off-policy gradient estimation for deep reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Gu"},{"key":"ref46","first-page":"275","article-title":"Flatland competition 2020: MAPF and MARL for efficient train coordination on a grid world","volume-title":"Proc. Competition Demonstration Track (NeurIPS)","author":"Laurent"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TSSC.1968.300136"},{"key":"ref48","first-page":"476","article-title":"D* lite","volume-title":"Proc. 18th AAAI Conf. Artif. Intell. (AAAI)","author":"Koenig"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(98)00023-X"},{"key":"ref50","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref51","article-title":"Dota 2 with large scale deep reinforcement learning","author":"Berner","year":"2019","journal-title":"arXiv:1912.06680"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2103.01955"},{"key":"ref53","first-page":"2048","article-title":"Leveraging procedural generation to benchmark reinforcement learning","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Cobbe"},{"key":"ref54","article-title":"Population based training of neural networks","author":"Jaderberg","year":"2017","journal-title":"arXiv:1711.09846"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.1056"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560748"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10772360\/10236574.pdf?arnumber=10236574","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T19:02:34Z","timestamp":1733252554000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10236574\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":56,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2023.3303502","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}