{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T11:51:49Z","timestamp":1769860309556,"version":"3.49.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"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":[[2020,10,24]]},"DOI":"10.1109\/iros45743.2020.9341303","type":"proceedings-article","created":{"date-parts":[[2021,3,15]],"date-time":"2021-03-15T10:49:56Z","timestamp":1615805396000},"page":"11755-11762","source":"Crossref","is-referenced-by-count":10,"title":["Scaling Up Multiagent Reinforcement Learning for Robotic Systems: Learn an Adaptive Sparse Communication Graph"],"prefix":"10.1109","author":[{"given":"Chuangchuang","family":"Sun","sequence":"first","affiliation":[]},{"given":"Macheng","family":"Shen","sequence":"additional","affiliation":[]},{"given":"Jonathan P.","family":"How","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref32","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"sunehag","year":"2017"},{"key":"ref31","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11794","article-title":"Counterfactual multi-agent policy gradients","author":"foerster","year":"2018","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref30","first-page":"10","article-title":"Swarm robotics: From sources of inspiration to domains of application","author":"?ahin","year":"2004","journal-title":"Int Workshop on Swarm Robotics SAB2006"},{"key":"ref10","article-title":"QMIX: monotonic value function factorisation for deep multi-agent reinforcement learning","author":"rashid","year":"2018"},{"key":"ref11","article-title":"Learning transferable cooperative behavior in multi-agent teams","author":"agarwal","year":"2019"},{"key":"ref12","article-title":"Graph policy gradients for large scale robot control","author":"khan","year":"2019"},{"key":"ref13","article-title":"Graph convolutional reinforcement learning for multi-agent cooperation","volume":"2","author":"jiang","year":"2018"},{"key":"ref14","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref15","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref16","first-page":"1614","article-title":"From softmax to sparsemax: A sparse model of attention and multi-label classification","author":"martins","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"593","DOI":"10.1007\/978-3-319-93417-4_38","article-title":"Modeling relational data with graph convolutional networks","author":"schlichtkrull","year":"2018","journal-title":"European Semantic Web Conference"},{"key":"ref18","article-title":"Mean field multi-agent reinforcement learning","author":"yang","year":"2018"},{"key":"ref19","article-title":"Actor-attention-critic for multi-agent reinforcement learning","author":"iqbal","year":"2018"},{"key":"ref28","first-page":"43","article-title":"Networks, crowds, and markets: Reasoning about a highly connected world","volume":"9","author":"easley","year":"2012","journal-title":"Significance"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1080\/00223980.1946.9917275"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1287\/moor.27.4.819.297"},{"key":"ref29","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref5","article-title":"Guided deep reinforcement learning for swarm systems","author":"h\u00fcttenrauch","year":"2017"},{"key":"ref8","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1109\/TSMCC.2007.913919","article-title":"A comprehensive survey of multiagent reinforcement learning","volume":"38","author":"bu","year":"2008","journal-title":"IEEE Transactions on Systems Man and Cybernetics Part C (Applications and Reviews)"},{"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","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","author":"sunehag","year":"2018","journal-title":"Proc of International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref20","article-title":"Tarmac: Targeted multi-agent communication","author":"das","year":"2018"},{"key":"ref22","article-title":"Learning classifiers with fenchel-young losses: Generalized entropies, margins, and algorithms","author":"blondel","year":"2018"},{"key":"ref21","first-page":"3338","article-title":"A regularized framework for sparse and structured neural attention","author":"niculae","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1223"},{"key":"ref23","first-page":"6422","article-title":"On controllable sparse alternatives to softmax","author":"laha","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref26","first-page":"1239","article-title":"Incorporating functional knowledge in neural networks","volume":"10","author":"dugas","year":"2009","journal-title":"Journal of Machine Learning Research"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.2174\/97816080576031130101"}],"event":{"name":"2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Las Vegas, NV, USA","start":{"date-parts":[[2020,10,24]]},"end":{"date-parts":[[2021,1,24]]}},"container-title":["2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9340668\/9340635\/09341303.pdf?arnumber=9341303","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T01:15:21Z","timestamp":1698023721000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9341303\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,24]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/iros45743.2020.9341303","relation":{},"subject":[],"published":{"date-parts":[[2020,10,24]]}}}