{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T18:24:10Z","timestamp":1729621450343,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"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":[[2019,7]]},"DOI":"10.1109\/ijcnn.2019.8852293","type":"proceedings-article","created":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T03:44:32Z","timestamp":1569901472000},"page":"1-8","source":"Crossref","is-referenced-by-count":8,"title":["Multi-Agent Deep Reinforcement Learning with Emergent Communication"],"prefix":"10.1109","author":[{"given":"David","family":"Simoes","sequence":"first","affiliation":[]},{"given":"Nuno","family":"Lau","sequence":"additional","affiliation":[]},{"given":"Luis Paulo","family":"Reis","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"2137","article-title":"Learning to communicate with deep multi-agent reinforcement learning","author":"foerster","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"Multiagent bidirectionally-coordinated nets for learning to play starcraft combat games","author":"peng","year":"2017","journal-title":"CoRR"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Learning representations by back-propagating errors","volume":"323","author":"rumelhart","year":"1986","journal-title":"Nature"},{"key":"ref13","first-page":"157","article-title":"Littman. Markov games as a framework for multi-agent reinforcement learning","author":"l","year":"1994","journal-title":"Proceedings of the Eleventh International Conference on International Conference on Machine Learning"},{"key":"ref14","first-page":"746","article-title":"The dynamics of reinforcement learning in cooperative multiagent systems","author":"claus","year":"1998","journal-title":"Proceedings of the fifteenth national\/tenth conference on Artificial intelligence\/Innovative applications of artificial intelligence"},{"key":"ref15","first-page":"1310","article-title":"On the difficulty of training recurrent neural networks","author":"pascanu","year":"2013","journal-title":"International Conference on Machine Learning"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11492","article-title":"Emergence of grounded compositional language in multi-agent populations","author":"mordatch","year":"2018","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1259"},{"key":"ref18","article-title":"Learning of coordination policies for robotic swarms","author":"li","year":"2017","journal-title":"CoRR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.321"},{"key":"ref28","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2016","journal-title":"International Conference on Learning Representations"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00025-9"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICUAS.2014.6842301"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88063-9_24"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/191246.191322"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511811654"},{"key":"ref8","first-page":"2244","article-title":"Learning multiagent communication with backpropagation","author":"sukhbaatar","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref7","first-page":"17","article-title":"Cool: A language for describing coordination in multi agent systems","author":"barbuceanu","year":"1995","journal-title":"ICMAS"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.5772\/5130"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33515-0_59"},{"key":"ref1","first-page":"195","article-title":"Planning, learning and coordination in multiagent decision processes","author":"boutilier","year":"1996","journal-title":"Proceedings of the 6th Conference on Theoretical Aspects of Rationality and Knowledge"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref22","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":"ref21","article-title":"Multi-agent cooperation and the emergence of (natural) language","author":"lazaridou","year":"2017","journal-title":"Proceedings of the International Conference on Learning Representations"},{"key":"ref24","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics volume 9 of Proceedings of Machine Learning Research"},{"key":"ref23","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-27149-1_30"},{"key":"ref25","article-title":"Adam: A method for stochastic op-timization","author":"kingma","year":"2015","journal-title":"3rd International Conference for Learning Representations"}],"event":{"name":"2019 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2019,7,14]]},"location":"Budapest, Hungary","end":{"date-parts":[[2019,7,19]]}},"container-title":["2019 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8840768\/8851681\/08852293.pdf?arnumber=8852293","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T16:30:26Z","timestamp":1664555426000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8852293\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2019.8852293","relation":{},"subject":[],"published":{"date-parts":[[2019,7]]}}}