{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,4]],"date-time":"2025-07-04T05:19:11Z","timestamp":1751606351743,"version":"3.28.0"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"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":[[2023,6,18]]},"DOI":"10.1109\/ijcnn54540.2023.10191629","type":"proceedings-article","created":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T17:30:03Z","timestamp":1690997403000},"page":"1-9","source":"Crossref","is-referenced-by-count":1,"title":["Attentional Opponent Modelling for Multi-agent Cooperation"],"prefix":"10.1109","author":[{"given":"Siyang","family":"Tan","sequence":"first","affiliation":[{"name":"Chinese Aeronautical Establishment,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Binqiang","family":"Chen","sequence":"additional","affiliation":[{"name":"Beihang University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"lowe","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref35","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":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6212"},{"key":"ref34","volume":"135","author":"sutton","year":"1998","journal-title":"Introduction to Reinforcement Learning"},{"key":"ref15","first-page":"4295","article-title":"Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning","author":"rashid","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref14","first-page":"7265","article-title":"Learning attentional communication for multi-agent cooperation","author":"jiang","year":"0","journal-title":"Advances in Neural Information Processing Systems 31 Annual Conference on Neural Information Processing Systems 2018"},{"key":"ref36","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1287\/moor.27.4.819.297"},{"key":"ref30","first-page":"3230","article-title":"Efficient communication in multi-agent reinforcement learning via variance based control","author":"zhang","year":"0","journal-title":"Annual Conference on Neural Information Processing Systems"},{"journal-title":"Starcraft official game site","year":"0","author":"blizzard","key":"ref11"},{"key":"ref33","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref10","first-page":"4218","article-title":"Machine theory of mind","author":"rabinowitz","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref32","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/science.aau6249"},{"journal-title":"Openai five","year":"2018","key":"ref1"},{"key":"ref17","article-title":"Multi-agent reinforcement learning: A selective overview of theories and algorithms","author":"zhang","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref39","article-title":"Graph attention networks","author":"veli?kovi?","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-019-09421-1"},{"key":"ref38","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref19","first-page":"374","article-title":"Iterative solution of games by fictitious play","volume":"13","author":"brown","year":"1951","journal-title":"Activity Analysis of Production and Allocation"},{"key":"ref18","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","author":"sunehag","year":"0","journal-title":"Proc of International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref24","article-title":"Probabilistic recursive reasoning for multi-agent reinforcement learning","author":"wen","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref23","first-page":"122","article-title":"Learning with opponent-learning awareness","author":"foerster","year":"0","journal-title":"In International Journal of Autonomous Agents and Multi Agent Systems"},{"key":"ref26","first-page":"19 210","article-title":"Agent modelling under partial observability for deep reinforcement learning","author":"papoudakis","year":"2021","journal-title":"Advances in Neural Information Processing Systems 34 Annual Conference on Neural Information Processing Systems 2021 NeurIPS 2021"},{"key":"ref25","first-page":"1802","article-title":"Learning policy representations in multiagent systems","author":"grover","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref20","first-page":"575","article-title":"Learning latent representations to influence multi-agent interaction","volume":"155","author":"xie","year":"0","journal-title":"Conference on Robot Learning ser Proceedings of Machine Learning Research"},{"key":"ref42","article-title":"Learning individually inferred communication for multi-agent cooperation","author":"ding","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2015.7280484"},{"key":"ref22","article-title":"The optimal control of partially observable markov processes","author":"sondik","year":"1971","journal-title":"STANFORD UNIV CA STANFORD ELECTRONICS LABS Tech Rep"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1579"},{"key":"ref43","first-page":"2186","article-title":"The starcraft multi-agent challenge","author":"samvelyan","year":"0","journal-title":"Proc of International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref28","article-title":"Multiagent bidirectionally-coordinated nets: Emergence of human-level coordination in learning to play starcraft combat games","author":"peng","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref27","first-page":"2244","article-title":"Learning multiagent communication with backpropagation","author":"sukhbaatar","year":"0","journal-title":"Advances in Neural information Processing Systems 29 Annual Conference on Neural Information Processing Systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5957"},{"key":"ref8","first-page":"1804","article-title":"Opponent modeling in deep reinforcement learning","author":"he","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2018.01.002"},{"key":"ref9","first-page":"4257","article-title":"Modeling others using oneself in multi-agent reinforcement learning","author":"raileanu","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v26i1.8380"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2012.2219061"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2006.02.006"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2901791"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2503"}],"event":{"name":"2023 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2023,6,18]]},"location":"Gold Coast, Australia","end":{"date-parts":[[2023,6,23]]}},"container-title":["2023 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10190990\/10190992\/10191629.pdf?arnumber=10191629","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T17:45:17Z","timestamp":1692639917000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10191629\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,18]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/ijcnn54540.2023.10191629","relation":{},"subject":[],"published":{"date-parts":[[2023,6,18]]}}}