{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T14:29:08Z","timestamp":1774448948615,"version":"3.50.1"},"reference-count":24,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,12]]},"DOI":"10.1109\/cdc.2016.7799442","type":"proceedings-article","created":{"date-parts":[[2017,1,5]],"date-time":"2017-01-05T17:11:18Z","timestamp":1483636278000},"page":"7592-7597","source":"Crossref","is-referenced-by-count":12,"title":["Large-scale multi-agent reinforcement learning using image-based state representation"],"prefix":"10.1109","author":[{"given":"Tianshu","family":"Chu","sequence":"first","affiliation":[]},{"given":"Shuhui","family":"Qu","sequence":"additional","affiliation":[]},{"given":"Jie","family":"Wang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"Multi-agent reinforcement learning: a critical survey","author":"shoham","year":"2003","journal-title":"Web manuscript"},{"key":"ref11","first-page":"133","article-title":"Networked distributed pomdps: A synthesis of distributed constraint optimization and pomdps","volume":"5","author":"nair","year":"2005","journal-title":"AAAI"},{"key":"ref12","first-page":"1523","article-title":"Multiagent planning with factored mdps","volume":"1","author":"guestrin","year":"2001","journal-title":"NIPS"},{"key":"ref13","first-page":"1789","article-title":"Collaborative multiagent reinforcement learning by payoff propagation","volume":"7","author":"kok","year":"2006","journal-title":"The Journal of Machine Learning Research"},{"key":"ref14","first-page":"299","article-title":"Decentralised coordination of mobile sensors using the max-sum algorithm","volume":"9","author":"stranders","year":"2009","journal-title":"IJCAI"},{"key":"ref15","author":"wiering","year":"2000","journal-title":"Multi-agent Reinforcement Learning for Traffic Light Control"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v25i1.7886","article-title":"Coordinated multi-agent reinforcement learning in networked distributed pomdps","author":"zhang","year":"2011","journal-title":"AAAI"},{"key":"ref17","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref19","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017928328829"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/9.580874"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2011.2106494"},{"key":"ref5","article-title":"Tree-based batch mode reinforcement learning","volume":"6","author":"ernst","year":"2005","journal-title":"Journal of Machine Learning Research"},{"key":"ref8","first-page":"227","article-title":"Coordinated reinforcement learning","volume":"2","author":"guestrin","year":"2002","journal-title":"ICML"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2014.7039557"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1512\/iumj.1957.6.56038"},{"key":"ref9","first-page":"1789","article-title":"Collaborative multiagent reinforcement learning by payoff propagation","volume":"7","author":"kok","year":"2006","journal-title":"Journal of Machine Learning Research"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50040-2"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1561\/2200000016"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"}],"event":{"name":"2016 IEEE 55th Conference on Decision and Control (CDC)","location":"Las Vegas, NV, USA","start":{"date-parts":[[2016,12,12]]},"end":{"date-parts":[[2016,12,14]]}},"container-title":["2016 IEEE 55th Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7786694\/7798233\/07799442.pdf?arnumber=7799442","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,14]],"date-time":"2025-06-14T01:22:43Z","timestamp":1749864163000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7799442\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,12]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/cdc.2016.7799442","relation":{},"subject":[],"published":{"date-parts":[[2016,12]]}}}