{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T07:13:40Z","timestamp":1766733220560},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,8]]},"abstract":"<jats:p>We present a method enabling a large number of agents to learn how to flock. This problem has drawn a lot of interest but requires many structural assumptions and is tractable only in small dimensions. We phrase this problem as a Mean Field Game (MFG),  where each individual chooses its own acceleration depending on the population behavior. Combining Deep Reinforcement Learning (RL) and Normalizing Flows (NF), we obtain a tractable solution requiring only very weak assumptions. Our algorithm finds a Nash Equilibrium and the agents adapt their velocity to match the neighboring flock\u2019s average one. We use Fictitious Play and alternate: (1) computing an approximate best response with Deep RL, and (2) estimating the next population distribution with NF. We show numerically that our algorithm can learn multi-group or high-dimensional flocking with obstacles.<\/jats:p>","DOI":"10.24963\/ijcai.2021\/50","type":"proceedings-article","created":{"date-parts":[[2021,8,11]],"date-time":"2021-08-11T07:00:49Z","timestamp":1628665249000},"page":"356-362","source":"Crossref","is-referenced-by-count":8,"title":["Mean Field Games Flock! The Reinforcement Learning Way"],"prefix":"10.24963","author":[{"given":"Sarah","family":"Perrin","sequence":"first","affiliation":[{"name":"Univ. Lille, CNRS, Inria, Centrale Lille, UMR 9189 CRIStAL"}]},{"given":"Mathieu","family":"Lauri\u00e8re","sequence":"additional","affiliation":[{"name":"Princeton University, ORFE"}]},{"given":"Julien","family":"P\u00e9rolat","sequence":"additional","affiliation":[{"name":"DeepMind Paris"}]},{"given":"Matthieu","family":"Geist","sequence":"additional","affiliation":[{"name":"Google Research, Brain Team"}]},{"given":"Romuald","family":"\u00c9lie","sequence":"additional","affiliation":[{"name":"Deepmind Paris"}]},{"given":"Olivier","family":"Pietquin","sequence":"additional","affiliation":[{"name":"Google Research, Brain Team"}]}],"member":"10584","event":{"number":"30","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"acronym":"IJCAI-2021","name":"Thirtieth International Joint Conference on Artificial Intelligence {IJCAI-21}","start":{"date-parts":[[2021,8,19]]},"theme":"Artificial Intelligence","location":"Montreal, Canada","end":{"date-parts":[[2021,8,27]]}},"container-title":["Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2021,8,11]],"date-time":"2021-08-11T07:01:06Z","timestamp":1628665266000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2021\/50"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2021,8]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2021\/50","relation":{},"subject":[],"published":{"date-parts":[[2021,8]]}}}