{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T20:05:05Z","timestamp":1730232305017,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,28]],"date-time":"2023-05-28T00:00:00Z","timestamp":1685232000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,28]],"date-time":"2023-05-28T00:00:00Z","timestamp":1685232000000},"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":[[2023,5,28]]},"DOI":"10.1109\/icc45041.2023.10278640","type":"proceedings-article","created":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T13:54:10Z","timestamp":1698069250000},"page":"5173-5178","source":"Crossref","is-referenced-by-count":2,"title":["Low Entropy Communication in Multi-Agent Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Lebin","family":"Yu","sequence":"first","affiliation":[{"name":"Tsinghua University,BNRist,Department of Electronic Engineering,Beijing,China,100084"}]},{"given":"Yunbo","family":"Qiu","sequence":"additional","affiliation":[{"name":"Tsinghua University,BNRist,Department of Electronic Engineering,Beijing,China,100084"}]},{"given":"Qiexiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University,BNRist,Department of Electronic Engineering,Beijing,China,100084"}]},{"given":"Xudong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University,BNRist,Department of Electronic Engineering,Beijing,China,100084"}]},{"given":"Jian","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University,BNRist,Department of Electronic Engineering,Beijing,China,100084"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Learning to schedule communication in multi -agent reinforcement learning","author":"kim","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref12","article-title":"Learning selective communication for multi-agent path finding","author":"ma","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref15","article-title":"Importance-aware message exchange and prediction for multi-agent reinforcement learning","author":"xiufeng","year":"0","journal-title":"2022 IEEE Global Communications Conference"},{"key":"ref14","article-title":"Minimizing communication while maximizing performance in multi-agent reinforcement learning","author":"vijay","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref11","first-page":"11 755","article-title":"Scaling up multi agent reinforcement learning for robotic systems: Learn an adaptive sparse communication graph","author":"sun","year":"0","journal-title":"2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341762"},{"key":"ref2","first-page":"2","article-title":"Heterogeneous multi-agent deep reinforcement learning for traffic lights control","author":"calvo","year":"2018","journal-title":"AICS"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197209"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"key":"ref16","article-title":"Event-triggered communication network with limited-bandwidth constraint for multi-agent reinforcement learning","author":"hu","year":"2021","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"ref19","article-title":"Learning nearly decompos-able value functions via communication minimization","author":"wang","year":"0","journal-title":"International Conference on Learning Representations"},{"journal-title":"Elements of Information Theory","year":"1999","author":"cover","key":"ref18"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref23","first-page":"1538","article-title":"Tarmac: Targeted multi-agent communication","author":"das","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref26","article-title":"The information bottleneck method","author":"tishby","year":"2000","journal-title":"Arxiv Preprint Physics\/0004057"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref20","first-page":"9908","article-title":"Learning ef-ficient multi-agent communication: An information bottleneck approach","author":"wang","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref22","article-title":"Learning when to communicate at scale in multi agent cooperative and competitive tasks","author":"singh","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref21","article-title":"Succinct and robust multi-agent communication with temporal message control","volume":"33","author":"zhang","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1002\/aic.690370209"},{"key":"ref27","first-page":"2244","article-title":"Learning multi agent communication with backpropagation","volume":"29","author":"sukhbaatar","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref8","article-title":"Tom2c: Target-oriented multi-agent communication and cooperation with theory of mind","author":"wang","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref7","article-title":"Communication in multi-agent rein-forcement learning: Intention sharing","author":"kim","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref9","first-page":"10088","article-title":"Learning multi-agent communication through structured attentive reasoning","volume":"33","author":"rangwala","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref4","first-page":"2137","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume":"29","author":"foerster","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219993"},{"key":"ref6","article-title":"Multi-agent reinforcement learning for networked system control","author":"chu","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref5","article-title":"Correcting experience replay for multi-agent communication","author":"ahilan","year":"0","journal-title":"International Conference on Learning Representations"}],"event":{"name":"ICC 2023 - IEEE International Conference on Communications","start":{"date-parts":[[2023,5,28]]},"location":"Rome, Italy","end":{"date-parts":[[2023,6,1]]}},"container-title":["ICC 2023 - IEEE International Conference on Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10278505\/10278554\/10278640.pdf?arnumber=10278640","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T14:04:20Z","timestamp":1699884260000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10278640\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,28]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icc45041.2023.10278640","relation":{},"subject":[],"published":{"date-parts":[[2023,5,28]]}}}