{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T15:18:18Z","timestamp":1773155898823,"version":"3.50.1"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"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":[],"published-print":{"date-parts":[[2021,9,27]]},"DOI":"10.1109\/iros51168.2021.9636344","type":"proceedings-article","created":{"date-parts":[[2021,12,16]],"date-time":"2021-12-16T15:45:38Z","timestamp":1639669538000},"page":"4785-4791","source":"Crossref","is-referenced-by-count":22,"title":["Scalable Reinforcement Learning Policies for Multi-Agent Control"],"prefix":"10.1109","author":[{"given":"Christopher D.","family":"Hsu","sequence":"first","affiliation":[]},{"given":"Heejin","family":"Jeong","sequence":"additional","affiliation":[]},{"given":"George J.","family":"Pappas","sequence":"additional","affiliation":[]},{"given":"Pratik","family":"Chaudhari","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"Task allocation via self-organizing swarm coalitions in distributed mobile sensor network","author":"low","year":"2004","journal-title":"Proceedings of the National Conference on Artificial Intelligence"},{"key":"ref38","article-title":"A structured prediction approach for generalization in cooperative multi-agent reinforcement learning","author":"carion","year":"2019"},{"key":"ref33","article-title":"Pic: Permutation invariant critic for multi-agent deep reinforcement learning","author":"liu","year":"2019"},{"key":"ref32","article-title":"Deep implicit coordination graphs for multi-agent reinforcement learning","author":"li","year":"2021"},{"key":"ref31","article-title":"Qtran: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","author":"son","year":"2019"},{"key":"ref30","article-title":"Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning","author":"rashid","year":"2018"},{"key":"ref37","article-title":"Actor-attention-critic for multi-agent reinforcement learning","author":"iqbal","year":"2019"},{"key":"ref36","article-title":"Emergent tool use from multi-agent autocurricula","author":"baker","year":"2020"},{"key":"ref35","article-title":"Roma: Multi-agent reinforcement learning with emergent roles","author":"wang","year":"2020"},{"key":"ref34","article-title":"Multiagent cooperation and competition with deep reinforcement learning","author":"tampuu","year":"2015"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"ref40","first-page":"315","article-title":"Autonomic mobile sensor network with self-coordinated task allocation and execution","volume":"36","author":"low","year":"2005","journal-title":"IEEE Transactions on Systems Man and Cypernetics–Part C Applications and Reviews"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref12","article-title":"Revisiting parameter sharing in multi-agent deep reinforcement learning","author":"terry","year":"2020"},{"key":"ref13","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2020"},{"key":"ref14","article-title":"Learning to track dynamic targets in partially known environments","author":"jeong","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.23919\/ACC45564.2020.9147901"},{"key":"ref16","article-title":"Deep sets","author":"zaheer","year":"2017"},{"key":"ref17","article-title":"Attention is all you need","author":"vaswani","year":"2017"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459468"},{"key":"ref19","article-title":"Maximum entropy inverse reinforcement learning","author":"ziebart","year":"2008"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139863"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2011.2181683"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9030082"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MPRV.2004.17"},{"key":"ref6","article-title":"Optimally solving dec-pomdps as continuous-state mdps","volume":"55","author":"dibangoye","year":"2013"},{"key":"ref29","article-title":"Counterfactual multi-agent policy gradients","author":"foerster","year":"2017"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2794608"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968173"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"1071","DOI":"10.1287\/opre.21.5.1071","article-title":"The optimal control of partially observable markov processes over a finite horizon","volume":"21","author":"smallwood","year":"1973","journal-title":"Operations Research"},{"key":"ref2","article-title":"An intelligent sensor management framework for pervasive surveillance","author":"hilal","year":"2013"},{"key":"ref9","article-title":"Information acquisition with sensing robots: Algorithms and error bounds","author":"atanasov","year":"2013"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.2514\/6.2006-6453"},{"key":"ref20","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018"},{"key":"ref22","article-title":"Simple random search provides a competitive approach to reinforcement learning","author":"mania","year":"2018"},{"key":"ref21","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-17452-0_5"},{"key":"ref41","article-title":"Evolutionary population curriculum for scaling multi-agent reinforcement learning","author":"long","year":"2020"},{"key":"ref23","article-title":"Graph policy gradients for large scale robot control","author":"khan","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2014.6859219"},{"key":"ref25","author":"isaacs","year":"1954","journal-title":"Differential Games I Introduction"}],"event":{"name":"2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Prague, Czech Republic","start":{"date-parts":[[2021,9,27]]},"end":{"date-parts":[[2021,10,1]]}},"container-title":["2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9635848\/9635849\/09636344.pdf?arnumber=9636344","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T12:54:48Z","timestamp":1652187288000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9636344\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,27]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/iros51168.2021.9636344","relation":{},"subject":[],"published":{"date-parts":[[2021,9,27]]}}}