{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:08:17Z","timestamp":1740100097271,"version":"3.37.3"},"reference-count":29,"publisher":"IEEE","funder":[{"DOI":"10.13039\/100000181","name":"Air Force Office of Scientific Research (AFSOR)","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000104","name":"National Aeronautics and Space Administration (NASA)","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000104","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation's","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,5,25]]},"DOI":"10.23919\/acc50511.2021.9483210","type":"proceedings-article","created":{"date-parts":[[2021,7,28]],"date-time":"2021-07-28T20:29:16Z","timestamp":1627504156000},"page":"1334-1339","source":"Crossref","is-referenced-by-count":2,"title":["Compositionality of Linearly Solvable Optimal Control in Networked Multi-Agent Systems"],"prefix":"10.23919","author":[{"given":"Lin","family":"Song","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Neng","family":"Wan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aditya","family":"Gahlawat","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Naira","family":"Hovakimyan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Evangelos A.","family":"Theodorou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1002\/9781118453988.ch6"},{"key":"ref11","article-title":"A unified theory of linearly solvable optimal control","volume":"1","author":"dvijotham","year":"2011","journal-title":"Artificial Intelligence (UAI)"},{"key":"ref12","first-page":"1856","article-title":"Compositionality of optimal control laws","author":"todorov","year":"2009","journal-title":"Advances in neural information processing systems"},{"key":"ref13","first-page":"2314","article-title":"Sample efficient path integral control under uncertainty","author":"pan","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1109\/MCS.2019.2949973","article-title":"The Robotarium: Globally impactful opportunities, challenges, and lessons learned in remote-access, distributed control of multirobot systems","volume":"40","author":"wilson","year":"2020","journal-title":"IEEE Control Systems Magazine"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2018.2856105"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2017.8317730"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2013.6760239"},{"key":"ref18","first-page":"310","article-title":"Taking DCOP to the real world: Efficient complete solutions for distributed event scheduling","author":"maheswaran","year":"0","journal-title":"International Joint Conference on Autonomous Agents and Multiagent Systems (AAMAS)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/508791.508804"},{"key":"ref28","article-title":"Compositionality of linearly solvable optimal control in networked multi-agent systems","author":"song","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.1995.478953"},{"key":"ref27","article-title":"Distributed algorithms for linearly-solvable optimal control in networked multi-agent systems","author":"wan","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(00)00050-9"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509336"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2016.7798507"},{"key":"ref5","first-page":"3137","article-title":"A generalized path integral control approach to reinforcement learning","volume":"11","author":"theodorou","year":"2010","journal-title":"Journal of Machine Learning Research"},{"key":"ref8","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11768-011-0313-y"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref2"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"11 478","DOI":"10.1073\/pnas.0710743106","article-title":"Efficient computation of optimal actions","volume":"106","author":"todorov","year":"0","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611974263"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917692864"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008942012299"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref24","article-title":"Multi-agent reinforcement learning: A selective overview of theories and algorithms","author":"zhang","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref23","first-page":"5872","article-title":"Fully decentralized multi-agent reinforcement learning with networked agents","volume":"80","author":"zhang","year":"0","journal-title":"Proceedings of the 35th International Conference on Machine Learning"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21236\/ADA440183"},{"key":"ref25","first-page":"4190","article-title":"A unified game-theoretic approach to multiagent reinforcement learning","author":"lanctot","year":"2017","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2021 American Control Conference (ACC)","start":{"date-parts":[[2021,5,25]]},"location":"New Orleans, LA, USA","end":{"date-parts":[[2021,5,28]]}},"container-title":["2021 American Control Conference (ACC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9482409\/9482614\/09483210.pdf?arnumber=9483210","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,5]],"date-time":"2023-01-05T20:02:59Z","timestamp":1672948979000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9483210\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,25]]},"references-count":29,"URL":"https:\/\/doi.org\/10.23919\/acc50511.2021.9483210","relation":{},"subject":[],"published":{"date-parts":[[2021,5,25]]}}}