{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:42:21Z","timestamp":1730230941541,"version":"3.28.0"},"reference-count":15,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9053534","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"3547-3551","source":"Crossref","is-referenced-by-count":3,"title":["Stabilizing Multi-Agent Deep Reinforcement Learning by Implicitly Estimating Other Agents\u2019 Behaviors"],"prefix":"10.1109","author":[{"given":"Yue","family":"Jin","sequence":"first","affiliation":[]},{"given":"Shuangqing","family":"Wei","sequence":"additional","affiliation":[]},{"given":"Jian","family":"Yuan","sequence":"additional","affiliation":[]},{"given":"Xudong","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Chao","family":"Wang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"871","article-title":"Extending q-learning to general adaptive multi-agent systems","author":"tesauro","year":"2004","journal-title":"Advances in neural information processing systems"},{"key":"ref11","first-page":"1146","article-title":"Stabilising experience replay for deep multi-agent reinforcement learning","author":"foerster","year":"2017","journal-title":"Proceedings of International Conference on Machine Learning"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/ICASSP.2019.8682555"},{"year":"2019","author":"barde","article-title":"Promoting coordination through policy regularization in multi-agent reinforcement learning","key":"ref13"},{"key":"ref14","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","author":"iqbal","year":"2019","journal-title":"Proceedings of International Conference on Machine Learning"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1007\/978-3-319-71682-4_5"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/ICRA.2017.7989385"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1038\/nature16961"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1371\/journal.pone.0172395"},{"year":"2013","author":"mnih","article-title":"Playing atari with deep reinforcement learning","key":"ref5"},{"key":"ref8","first-page":"2974","article-title":"Counterfactual multi-agent policy gradients","author":"foerster","year":"2018","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref7","first-page":"2681","article-title":"Deep decentralized multi-task multi-agent reinforcement learning under partial observability","author":"omidshafiei","year":"2017","journal-title":"Proceedings of International Conference on Machine Learning"},{"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"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref9","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"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2020,5,4]]},"location":"Barcelona, Spain","end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09053534.pdf?arnumber=9053534","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:23:54Z","timestamp":1656375834000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053534\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":15,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053534","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}