{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T07:35:42Z","timestamp":1750836942138,"version":"3.40.3"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030868543"},{"type":"electronic","value":"9783030868550"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-86855-0_12","type":"book-chapter","created":{"date-parts":[[2021,10,4]],"date-time":"2021-10-04T22:58:16Z","timestamp":1633388296000},"page":"169-179","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Q-Mixing Network for Multi-agent Pathfinding in Partially Observable Grid Environments"],"prefix":"10.1007","author":[{"given":"Vasilii","family":"Davydov","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexey","family":"Skrynnik","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Konstantin","family":"Yakovlev","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aleksandr","family":"Panov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,10,4]]},"reference":[{"key":"12_CR1","doi-asserted-by":"crossref","unstructured":"Barer, M., Sharon, G., Stern, R., Felner, A.: Suboptimal variants of the conflict-based search algorithm for the multi-agent pathfinding problem. In: Proceedings of The 7th Annual Symposium on Combinatorial Search (SoCS 2014), pp. 19\u201327 (July 2014)","DOI":"10.1609\/socs.v5i1.18315"},{"key":"12_CR2","unstructured":"Boyarski, E., et al.: ICBS: Improved conflict-based search algorithm for multi-agent pathfinding. In: Proceedings of The 24th International Joint Conference on Artificial Intelligence (IJCAI 2015), pp. 740\u2013746 (2015)"},{"issue":"3","key":"12_CR3","doi-asserted-by":"publisher","first-page":"835","DOI":"10.1109\/TASE.2015.2445780","volume":"12","author":"M \u010c\u00e1p","year":"2015","unstructured":"\u010c\u00e1p, M., Nov\u00e1k, P., Kleiner, A., Seleck\u00fd, M.: Prioritized planning algorithms for trajectory coordination of multiple mobile robots. IEEE Trans. Autom. Sci. Eng. 12(3), 835\u2013849 (2015)","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"12_CR4","unstructured":"Ha, D., Dai, A., Le, Q.V.: Hypernetworks. In: Proceedings of the International Conference on Learning Representations (2016)"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Felner, A., Li, J., Boyarski, E., Ma, H., Cohen, L., Kumar, T. S., Koenig, S.: Adding heuristics to conflict-based search for multi-agent path finding. In: Proceedings of the 28th International Conference on Automated Planning and Scheduling (ICAPS 2018), pp. 83\u201387 (2018)","DOI":"10.1609\/icaps.v28i1.13883"},{"key":"12_CR6","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1007\/978-3-030-52152-3_18","volume-title":"Artificial General Intelligence","author":"A Gorodetskiy","year":"2020","unstructured":"Gorodetskiy, A., Shlychkova, A., Panov, A.I.: Delta schema network in model-based reinforcement learning. In: Goertzel, B., Panov, A.I., Potapov, A., Yampolskiy, R. (eds.) AGI 2020. LNCS (LNAI), vol. 12177, pp. 172\u2013182. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-52152-3_18"},{"key":"12_CR7","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1007\/978-3-030-59535-7_6","volume-title":"Artificial Intelligence","author":"M Martinson","year":"2020","unstructured":"Martinson, M., Skrynnik, A., Panov, A.I.: Navigating autonomous vehicle at the road intersection simulator with reinforcement learning. In: Kuznetsov, S.O., Panov, A.I., Yakovlev, K.S. (eds.) RCAI 2020. LNCS (LNAI), vol. 12412, pp. 71\u201384. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-59535-7_6"},{"issue":"7540","key":"12_CR8","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"key":"12_CR9","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1016\/j.procs.2018.01.054","volume":"123","author":"AI Panov","year":"2018","unstructured":"Panov, A.I., Yakovlev, K.S., Suvorov, R.: Grid path planning with deep reinforcement learning: preliminary results. Procedia Comput. Sci. 123, 347\u2013353 (2018)","journal-title":"Procedia Comput. Sci."},{"key":"12_CR10","unstructured":"Rashid, T., Samvelyan, M., Schroeder, C., Farquhar, G., Foerster, J., Whiteson, S.: Qmix: monotonic value function factorisation for deep multi-agent reinforcement learning. In: International Conference on Machine Learning, PMLR, pp. 4295\u20134304 (2018)"},{"issue":"3","key":"12_CR11","doi-asserted-by":"publisher","first-page":"2378","DOI":"10.1109\/LRA.2019.2903261","volume":"4","author":"G Sartoretti","year":"2019","unstructured":"Sartoretti, G., et al.: Primal: pathfinding via reinforcement and imitation multi-agent learning. IEEE Robot. Autom. Lett. 4(3), 2378\u20132385 (2019)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"12_CR12","unstructured":"Schrittwieser, J., Hubert, T., Mandhane, A., Barekatain, M., Antonoglou, I., Silver, D.: Online and Offline Reinforcement Learning by Planning with a Learned Model (2021)"},{"key":"12_CR13","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"Sharon, G., Stern, R., Felner, A., Sturtevant., N.R.: Conflict-based search for optimal multiagent path finding. Artif. Intell. J. 218, 40\u201366 (2015)","DOI":"10.1016\/j.artint.2014.11.006"},{"key":"12_CR15","series-title":"Advances in Intelligent Systems and Computing","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1007\/978-3-030-25719-4_64","volume-title":"Biologically Inspired Cognitive Architectures 2019","author":"M Shikunov","year":"2020","unstructured":"Shikunov, M., Panov, A.I.: Hierarchical reinforcement learning approach for the road intersection task. In: Samsonovich, A.V. (ed.) BICA 2019. AISC, vol. 948, pp. 495\u2013506. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-25719-4_64"},{"key":"12_CR16","unstructured":"Sunehag, P., et al.: Value-decomposition networks for cooperative multi-agent learning based on team reward. In: Proceedings of the 17th International Conference on Autonomous Agents and Multiagent Systems (2017)"},{"key":"12_CR17","unstructured":"Surynek, P., Felner, A., Stern, R., Boyarski, E.: Efficient sat approach to multi-agent path finding under the sum of costs objective. In: Proceedings of the 22nd European Conference on Artificial Intelligence (ECAI 2016), pp. 810\u2013818. IOS Press (2016)"},{"key":"12_CR18","doi-asserted-by":"publisher","unstructured":"van den Berg, J., Guy, S.J., Lin, M., Manocha, D.: Reciprocal n-body collision avoidance. In: Pradalier, C., Siegwart, R., Hirzinger, G. (eds.) Robotics Research. Springer Tracts in Advanced Robotics, vol. 70, pp. 3\u201319. Springer, Berlin (2011). https:\/\/doi.org\/10.1007\/978-3-642-19457-3_1","DOI":"10.1007\/978-3-642-19457-3_1"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"Yakovlev, K., Andreychuk, A., Vorobyev, V.: Prioritized multi-agent path finding for differential drive robots. In: Proceedings of the 2019 European Conference on Mobile Robots (ECMR 2019), IEEE, pp. 1\u20136 (2019)","DOI":"10.1109\/ECMR.2019.8870957"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-86855-0_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,11]],"date-time":"2023-01-11T02:10:41Z","timestamp":1673403041000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86855-0_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030868543","9783030868550"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86855-0_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"4 October 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"RCAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Russian Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Taganrog","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Russia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 October 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 October 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"rcai2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2021.rncai.ru\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"80","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"19","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"7","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"24% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2,9","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}