{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:20:39Z","timestamp":1740100839304,"version":"3.37.3"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T00:00:00Z","timestamp":1652659200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T00:00:00Z","timestamp":1652659200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,16]]},"DOI":"10.1109\/icc45855.2022.9838553","type":"proceedings-article","created":{"date-parts":[[2022,8,11]],"date-time":"2022-08-11T19:37:11Z","timestamp":1660246631000},"page":"4974-4979","source":"Crossref","is-referenced-by-count":0,"title":["Towards Distributed Communication and Control in Real-World Multi-Agent Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Jieyan","family":"Liu","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China"}]},{"given":"Yi","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China"}]},{"given":"Zhekai","family":"Du","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China"}]},{"given":"Ke","family":"Lu","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"article-title":"Learning to communicate to solve riddles with deep distributed recurrent q-networks","year":"2016","author":"foerster","key":"ref12"},{"key":"ref13","first-page":"2137","article-title":"Learning to communicate with deep multi-agent reinforcement learning","author":"foerster","year":"2016","journal-title":"NIPS"},{"key":"ref14","article-title":"Learning multiagent communication with backpropagation","author":"sukhbaatar","year":"2016","journal-title":"NIPS"},{"key":"ref15","article-title":"Learning when to communicate at scale in multiagent cooperative and competitive tasks","author":"singh","year":"2019","journal-title":"ICLRE"},{"key":"ref16","first-page":"1146","article-title":"Stabilising experience replay for deep multi-agent reinforcement learning","author":"foerster","year":"2017","journal-title":"ICML"},{"key":"ref17","article-title":"Continuous adaptation via meta-learning in nonstationary and competitive environments","author":"al-shedivat","year":"2018","journal-title":"ICLRE"},{"key":"ref18","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"2017","journal-title":"ICML"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"article-title":"Dealing with non-stationarity in multi-agent deep reinforcement learning","year":"2019","author":"papoudakis","key":"ref4"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/1868447.1868466"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2977374"},{"key":"ref6","first-page":"293","article-title":"A survey of real-time strategy game ai research and competition in starcraft","volume":"5","author":"ontan\u00f3n","year":"2013","journal-title":"T-CIAIG"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/11536406_4"},{"key":"ref8","first-page":"1","article-title":"Grandmaster level in starcraft ii using multi-agent reinforcement learning","author":"vinyals","year":"2019","journal-title":"Nature"},{"key":"ref7","article-title":"Rts games and real-time ai research","volume":"6370","author":"buro","year":"2004","journal-title":"BRIMS"},{"key":"ref2","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":"ref9","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888912000057"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref20","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"NIPS"},{"key":"ref22","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"ICML"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014213"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref23","first-page":"66","article-title":"Cooperative multi-agent control using deep reinforcement learning","author":"gupta","year":"2017","journal-title":"AAMAS"},{"article-title":"Starcraft ii: A new challenge for reinforcement learning","year":"2017","author":"vinyals","key":"ref26"},{"key":"ref25","article-title":"Prioritized experience replay","author":"schaul","year":"2016","journal-title":"ICLRE"}],"event":{"name":"ICC 2022 - IEEE International Conference on Communications","start":{"date-parts":[[2022,5,16]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2022,5,20]]}},"container-title":["ICC 2022 - IEEE International Conference on Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9837954\/9838246\/09838553.pdf?arnumber=9838553","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,5]],"date-time":"2022-09-05T20:29:25Z","timestamp":1662409765000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9838553\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,16]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icc45855.2022.9838553","relation":{},"subject":[],"published":{"date-parts":[[2022,5,16]]}}}