{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T21:12:36Z","timestamp":1777669956440,"version":"3.51.4"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Naval Research Lab","award":["N00173-21-1-G009"],"award-info":[{"award-number":["N00173-21-1-G009"]}]},{"name":"Lockheed Martin Corporation","award":["GR0-0000509"],"award-info":[{"award-number":["GR0-0000509"]}]},{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["N00014-19-1-2076"],"award-info":[{"award-number":["N00014-19-1-2076"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006234","name":"Sandia National Laboratories","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006234","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Robot."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tro.2024.3431829","type":"journal-article","created":{"date-parts":[[2024,7,22]],"date-time":"2024-07-22T18:13:33Z","timestamp":1721672013000},"page":"3833-3849","source":"Crossref","is-referenced-by-count":7,"title":["Heterogeneous Policy Networks for Composite Robot Team Communication and Coordination"],"prefix":"10.1109","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0147-1037","authenticated-orcid":false,"given":"Esmaeil","family":"Seraj","sequence":"first","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, GA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0773-8054","authenticated-orcid":false,"given":"Rohan","family":"Paleja","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, GA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9959-1678","authenticated-orcid":false,"given":"Luis","family":"Pimentel","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, GA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2098-3206","authenticated-orcid":false,"given":"Kin Man","family":"Lee","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, GA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6364-5074","authenticated-orcid":false,"given":"Zheyuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, GA, USA"}]},{"given":"Daniel","family":"Martin","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, GA, USA"}]},{"given":"Matthew","family":"Sklar","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, GA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7442-5920","authenticated-orcid":false,"given":"John","family":"Zhang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3506-5651","authenticated-orcid":false,"given":"Zahi","family":"Kakish","sequence":"additional","affiliation":[{"name":"Sandia National Laboratories, Albuquerque, NM, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5321-6038","authenticated-orcid":false,"given":"Matthew","family":"Gombolay","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, GA, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1037\/10690-004"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1037\/0021-9010.85.2.273"},{"key":"ref3","first-page":"35426","article-title":"Mixed-initiative multiagent apprenticeship learning for human training of robot teams","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Seraj","year":"2023"},{"key":"ref4","article-title":"Toward an understanding of team performance and training","volume-title":"Teams: Their Training and Performance","author":"Salas","year":"1992"},{"key":"ref5","article-title":"Iterated reasoning with mutual information in cooperative and Byzantine decentralized teaming","author":"Konan","year":"2022","journal-title":"Proc. Int. Conf. Learn. Representations"},{"key":"ref6","article-title":"The effects of interpersonal communication style on task performance and well being","author":"Taylor","year":"2007"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref8","first-page":"1101","article-title":"Coordinating multi-agent reinforcement learning with limited communication","volume-title":"Proc. Int. Conf. Auton. Agents Multiagent Syst.","author":"Zhang","year":"2013"},{"key":"ref9","first-page":"2297","article-title":"Coordinated multiagent reinforcement learning for teams of mobile sensing robots","volume-title":"Proc. 18th Int. Conf. Auton. Agents MultiAgent Syst.","author":"Yu","year":"2019"},{"key":"ref10","first-page":"1865","article-title":"Cooperative multi-agent deep reinforcement learning in soccer domains","volume-title":"Proc. 18th Int. Conf. Auton. Agents MultiAgent Syst.","author":"Ocana","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref12","article-title":"Dota 2 with large scale deep reinforcement learning","author":"Berner"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"ref14","first-page":"1538","article-title":"Tarmac: Targeted multi-agent communication","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Das","year":"2019"},{"key":"ref15","first-page":"456","article-title":"Learning correlated communication topology in multi-agent reinforcement learning","volume-title":"Proc. 20th Int. Conf. Auton. Agents MultiAgent Syst.","author":"Du","year":"2021"},{"key":"ref16","article-title":"Accnet: Actor-coordinator-critic net for learning-to-communicate with deep multi-agent reinforcement learning","author":"Mao","year":"2017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-020-09461-y"},{"key":"ref18","article-title":"Heterogeneous graph attention networks for learning diverse communication","author":"Seraj","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3096069"},{"key":"ref20","article-title":"Safe coordination of human-robot firefighting teams","author":"Seraj","year":"2019"},{"issue":"1","key":"ref21","first-page":"225","article-title":"Intermittent connectivity maintenance with heterogeneous robots","volume-title":"IEEE Trans. Robot.","volume":"37","author":"Aragues","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-022-09566-6"},{"key":"ref23","first-page":"1173","article-title":"Learning efficient diverse communication for cooperative heterogeneous teaming","volume-title":"Proc. Int. Conf. Adaptive Agents Multi-Agent Syst.","author":"Seraj","year":"2022"},{"key":"ref24","article-title":"Individualized controlled continuous communication model for multiagent cooperative and competitive tasks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Singh","year":"2019"},{"key":"ref25","first-page":"2244","article-title":"Learning multiagent communication with backpropagation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sukhbaatar","year":"2016"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6211"},{"key":"ref27","first-page":"7254","article-title":"Learning attentional communication for multi-agent cooperation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jiang","year":"2018"},{"key":"ref28","article-title":"Multi-agent reinforcement learning for networked system control","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Chu","year":"2020"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3056418"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i13.26928"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-019-05864-5"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.23919\/ACC45564.2020.9147613"},{"key":"ref33","first-page":"2137","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Foerster","year":"2016"},{"key":"ref34","article-title":"Learning to schedule communication in multi-agent reinforcement learning","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Kim","year":"2019"},{"key":"ref35","first-page":"964","article-title":"Multi-agent graph-attention communication and teaming","volume-title":"Proc. 20th Int. Conf. Auton. Agents MultiAgent Syst.","author":"Niu","year":"2021"},{"key":"ref36","first-page":"2974","article-title":"Counterfactual multi-agent policy gradients","volume-title":"Proc. 32nd AAAI Conf. Artif. Intell., 30th Innov. Appl. Artif. Intell., 8th AAAI Symp. Educ. Adv. Artif. Intell.","author":"Foerster","year":"2018"},{"key":"ref37","article-title":"Communication topologies between learning agents in deep reinforcement learning","author":"Adjodah","year":"2019"},{"key":"ref38","article-title":"Graph convolutional reinforcement learning","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Jiang","year":"2020"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-022-09580-8"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CSCI.2015.167"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICUSAI47366.2019.9124911"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.5753\/eniac.2020.12161"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS51040.2020.00031"},{"key":"ref44","article-title":"Multi-agent deep reinforcement learning with extremely noisy observations","author":"Kilinc","year":"2018"},{"issue":"2","key":"ref45","first-page":"487","article-title":"Online planning for multi-agent systems with bounded communication","volume-title":"Artif. Intell.","volume":"175","author":"Wu","year":"2011"},{"key":"ref46","first-page":"705","article-title":"Planning not to talk: Multiagent systems that are robust to communication loss","author":"Karabag","year":"2022","journal-title":"Proc. 21st Int. Conf. Auton. Agents Multiagent Syst."},{"key":"ref47","first-page":"7160","article-title":"Communication learning via backpropagation in discrete channels with unknown noise","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Freed","year":"2020"},{"key":"ref48","first-page":"1","article-title":"Learning-based physical layer communications for multi-agent collaboration","volume-title":"Proc. IEEE 30th Annu. Int. Symp. Pers. Indoor Mobile Radio Commun.","author":"Mostaani","year":"2019"},{"key":"ref49","doi-asserted-by":"crossref","DOI":"10.1109\/JSAC.2021.3087248","article-title":"Effective communications: A joint learning and communication framework for multi-agent reinforcement learning over noisy channels","author":"Tung","year":"2021"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(98)00023-X"},{"key":"ref51","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref52","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.01.001"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"ref55","article-title":"Graph attention networks","volume-title":"Proc. 6th Int. Conf. Learn. Representations","author":"Velikovi","year":"2018"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3002198"},{"key":"ref57","first-page":"3431","article-title":"Fully convolutional networks for semantic segmentation","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Shelhamer","year":"2014"},{"key":"ref58","article-title":"Categorical reparameterization with Gumbel-Softmax","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jang","year":"2017"},{"key":"ref59","article-title":"Collaboration of ai agents via cooperative multi-agent deep reinforcement learning","author":"Balachandar","year":"2019"},{"key":"ref60","first-page":"2576","article-title":"Grid-wise control for multi-agent reinforcement learning in video game ai","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Han","year":"2019"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341696"},{"key":"ref62","doi-asserted-by":"crossref","DOI":"10.2172\/2003731","article-title":"Scaling multi-agent reinforcement learning via state upsampling","author":"Pimentel","year":"2022"},{"key":"ref63","first-page":"2186","article-title":"The starcraft multi-agent challenge","volume-title":"Proc. 18th Int. Conf. Auton. Agents Multiagent Syst.","author":"Samvelyan","year":"2019"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-32037-8_4"},{"key":"ref65","article-title":"The surprising effectiveness of PPO in cooperative, multi-agent games","volume-title":"Proc. 36th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Yu","year":"2022"},{"key":"ref66","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Lowe","year":"2017"},{"key":"ref67","volume-title":"Digital Communications","year":"2007"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1002\/9781119765448.ch6"},{"key":"ref69","volume-title":"Low-Noise Electronic System Design","author":"Connelly","year":"1993"},{"key":"ref70","article-title":"Firecommander: An interactive, probabilistic multi-agent environment for joint perception-action tasks","author":"Seraj","year":"2020"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.2737\/rmrs-rp-4"},{"key":"ref72","first-page":"1173","article-title":"Learning efficient diverse communication for cooperative heterogeneous teaming","volume-title":"Proc. 21st Int. Conf. Auton. agents multiagent Syst.","author":"Seraj","year":"2022"},{"issue":"1","key":"ref73","first-page":"26","article-title":"The robotarium: Globally impactful opportunities, challenges, and lessons learned in remote-access, distributed control of multirobot systems","volume-title":"IEEE Control Syst.","volume":"40","author":"Wilson","year":"2020"}],"container-title":["IEEE Transactions on Robotics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8860\/10365208\/10606072.pdf?arnumber=10606072","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,13]],"date-time":"2024-08-13T05:13:36Z","timestamp":1723526016000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10606072\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/tro.2024.3431829","relation":{},"ISSN":["1552-3098","1941-0468"],"issn-type":[{"value":"1552-3098","type":"print"},{"value":"1941-0468","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}