{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T22:32:06Z","timestamp":1762036326299,"version":"build-2065373602"},"reference-count":21,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,3,24]]},"DOI":"10.1109\/ciss50987.2021.9400275","type":"proceedings-article","created":{"date-parts":[[2021,4,22]],"date-time":"2021-04-22T03:11:36Z","timestamp":1619061096000},"page":"1-6","source":"Crossref","is-referenced-by-count":3,"title":["Decentralized Multi-agent Reinforcement Learning with Shared Actions"],"prefix":"10.1109","author":[{"given":"Rajesh K","family":"Mishra","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deepanshu","family":"Vasal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sriram","family":"Vishwanath","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"66","article-title":"Cooperative Multiagent Control Using Deep Reinforcement Learning","volume":"10642 lnai","author":"gupta","year":"2017","journal-title":"Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2015.7172192"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1080\/10618600.1996.10474692","article-title":"Monte carlo filter and smoother for non-gaussian nonlinear state space models","volume":"5","author":"kitagawa","year":"1996","journal-title":"Journal of Computational and Graphical Statistics"},{"key":"ref13","first-page":"64","article-title":"comparison of resampling schemes for particle filtering","author":"douc","year":"2005","journal-title":"ISPA 2005 the 4th International Symposium on Image and Signal Processing and Analysis 2005 ISPA-05"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/78.984773"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2016.2637324"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2630"},{"key":"ref17","first-page":"337","article-title":"Particle Filter-based policy gradient in POMDPs","author":"coquelin","year":"0","journal-title":"Advances in Neural Information Processing Systems 21 - Proceedings of the 2008 Conference"},{"journal-title":"Statistics for Engineering and Information Science","year":"1999","author":"vapnik","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-0865-5_26"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2004.834433"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/301136.301195"},{"journal-title":"Regret Bounds for Decentralized Learning in Cooperative Multi-Agent Dynamical Systems","year":"2020","author":"asghari","key":"ref6"},{"journal-title":"Distributed value functions","year":"1999","author":"schneider","key":"ref5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029898"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2010.2089381"},{"journal-title":"The hanabi challenge a new frontier for ai research corr abs\/1902 00506 (2019)","year":"0","author":"bard","key":"ref2"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2013.2239000"},{"key":"ref9","first-page":"9340","article-title":"Fully decentralized multi-agent reinforcement learning with networked agents","volume":"13","author":"zhang","year":"0","journal-title":"ICML 2018-35th International Conference on Machine Learning"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1137\/S089548019223872X"},{"key":"ref21","article-title":"Reinforcement learning for mean-field teams","author":"subramanian","year":"0","journal-title":"Workshop on Adaptive and Learning Agents at International Conference on Autonomous Agents and Multi-Agent Systems"}],"event":{"name":"2021 55th Annual Conference on Information Sciences and Systems (CISS)","start":{"date-parts":[[2021,3,24]]},"location":"Baltimore, MD, USA","end":{"date-parts":[[2021,3,26]]}},"container-title":["2021 55th Annual Conference on Information Sciences and Systems (CISS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9400188\/9400208\/09400275.pdf?arnumber=9400275","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,29]],"date-time":"2024-08-29T01:23:39Z","timestamp":1724894619000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9400275\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,24]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/ciss50987.2021.9400275","relation":{},"subject":[],"published":{"date-parts":[[2021,3,24]]}}}