{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T08:47:25Z","timestamp":1767084445877,"version":"3.37.3"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","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":[[2020,10,24]]},"DOI":"10.1109\/iros45743.2020.9341376","type":"proceedings-article","created":{"date-parts":[[2021,3,15]],"date-time":"2021-03-15T14:49:56Z","timestamp":1615819796000},"page":"7985-7992","source":"Crossref","is-referenced-by-count":10,"title":["Cooperative Control of Mobile Robots with Stackelberg Learning"],"prefix":"10.1109","author":[{"given":"Joewie J.","family":"Koh","sequence":"first","affiliation":[{"name":"University of Colorado,Department of Computer Science,Boulder"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guohui","family":"Ding","sequence":"additional","affiliation":[{"name":"University of Colorado,Department of Computer Science,Boulder"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christoffer","family":"Heckman","sequence":"additional","affiliation":[{"name":"University of Colorado,Department of Computer Science,Boulder"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lijun","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Colorado,Department of Computer Science,Boulder"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alessandro","family":"Roncone","sequence":"additional","affiliation":[{"name":"University of Colorado,Department of Computer Science,Boulder"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref32","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.ress.2019.106695"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2016.2554079"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-28619-4_8"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.1996.570849"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TRA.2002.804500"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TRA.2002.803466"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202141"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202134"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1177\/0278364907085097"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref19","article-title":"Nash Q-learning for general-sum stochastic games","volume":"4","author":"hu","year":"2003","journal-title":"Journal of Machine Learning Research"},{"key":"ref28","first-page":"41","article-title":"Multiagent Q-learning: Preliminary study on dominance between the Nash and Stackelberg equilibriums","author":"laum\u00f4nier","year":"2005","journal-title":"2005 AAAI Workshop on Multiagent Learning"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2977374"},{"key":"ref27","first-page":"105","article-title":"Asymmetric multiagent reinforcement learning","volume":"2","author":"k\u00f6n\u00f6nen","year":"2004","journal-title":"Web Intelligence and Agent Systems An international Journal"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-017-9677-2"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-019-09421-1"},{"key":"ref29","article-title":"Learning expensive coordination: An event-based deep RL approach","author":"shi","year":"2020","journal-title":"International Conference on Learning Representations"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2004.839232"},{"key":"ref7","first-page":"267","article-title":"Decentralized motion planning for multiple robots subject to sensing and communication constraints","author":"pereira","year":"2003","journal-title":"International Workshop on Multi-Robot Systems 2003"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1108\/IR-07-2016-0194"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794265"},{"journal-title":"Tech Rep NISTIR 8022","year":"2015","author":"schneier","key":"ref1"},{"key":"ref20","first-page":"1831","article-title":"Distributed reinforcement learning for cooperative multi-robot object manipulation","author":"ding","year":"2020","journal-title":"International Joint Conference on Autonomous Agents and Multiagent Systems (AAMAS)"},{"key":"ref22","article-title":"Demand response management in smart grid networks: A two-stage game-theoretic learning-based approach","author":"apostolopoulos","year":"2018","journal-title":"Mobile Networks and Applications"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2909824.3020253"},{"key":"ref24","article-title":"Approximate solutions for partially observable stochastic games with common payoffs","author":"emery-montemerlo","year":"2004","journal-title":"Third International Joint Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593725"},{"key":"ref26","article-title":"Probabilistic recursive reasoning for multi-agent reinforcement learning","author":"wen","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref25","first-page":"705","article-title":"Taming decentralized POMDPs: Towards efficient policy computation for multiagent settings","author":"nair","year":"2003","journal-title":"Eighteenth International Joint Conference on Artificial Intelligence (IJCAI)"}],"event":{"name":"2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2020,10,24]]},"location":"Las Vegas, NV, USA","end":{"date-parts":[[2021,1,24]]}},"container-title":["2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9340668\/9340635\/09341376.pdf?arnumber=9341376","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T21:57:47Z","timestamp":1656453467000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9341376\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,24]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/iros45743.2020.9341376","relation":{},"subject":[],"published":{"date-parts":[[2020,10,24]]}}}