{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T09:58:48Z","timestamp":1764842328520,"version":"3.37.3"},"reference-count":18,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T00:00:00Z","timestamp":1585699200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T00:00:00Z","timestamp":1585699200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T00:00:00Z","timestamp":1585699200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"DOE Traineeship in Robotics","award":["DE-EM0004067"],"award-info":[{"award-number":["DE-EM0004067"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2020,4]]},"DOI":"10.1109\/lra.2020.2972862","type":"journal-article","created":{"date-parts":[[2020,2,11]],"date-time":"2020-02-11T02:00:05Z","timestamp":1581386405000},"page":"2498-2505","source":"Crossref","is-referenced-by-count":11,"title":["Simultaneous Policy and Discrete Communication Learning for Multi-Agent Cooperation"],"prefix":"10.1109","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3741-3709","authenticated-orcid":false,"given":"Benjamin","family":"Freed","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7579-9916","authenticated-orcid":false,"given":"Guillaume","family":"Sartoretti","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5434-7945","authenticated-orcid":false,"given":"Howie","family":"Choset","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"Emergence of grounded compositional language in multi-agent populations","author":"mordatch","year":"0","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2922493"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2903261"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-05816-6_3"},{"key":"ref14","first-page":"195","article-title":"Planning, learning and coordination in multiagent decision processes","author":"boutilier","year":"0","journal-title":"Proc 8th Conf Theoretical Aspects of Rationality and Knowledge"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1287\/moor.27.4.819.297"},{"key":"ref16","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"0","journal-title":"Proc 12th Int Conf Neural Inf Process Syst"},{"key":"ref17","article-title":"Variance reduction for policy gradient with action-dependent factorized baselines","author":"wu","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2012.2218595"},{"key":"ref4","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"ref6","first-page":"2137","article-title":"Learning to communicate with deep multi-agent reinforcement learning","author":"foerster","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref5","article-title":"Counterfactual multi-agent policy gradients","author":"foerster","year":"0","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-14435-6_7"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32723-0_24"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/science.aau6249"},{"year":"2018","key":"ref1","article-title":"Openai five"},{"key":"ref9","first-page":"2244","article-title":"Learning multiagent communication with backpropagation","author":"sukhbaatar","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/8932682\/08988235.pdf?arnumber=8988235","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:32:48Z","timestamp":1651080768000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8988235\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,4]]},"references-count":18,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/lra.2020.2972862","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"type":"electronic","value":"2377-3766"},{"type":"electronic","value":"2377-3774"}],"subject":[],"published":{"date-parts":[[2020,4]]}}}