{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T12:35:09Z","timestamp":1730205309461,"version":"3.28.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62136008,62276001,U21A20512"],"award-info":[{"award-number":["62136008,62276001,U21A20512"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003995","name":"Anhui Provincial Natural Science Foundation","doi-asserted-by":"publisher","award":["2308085J03,2208085MF174"],"award-info":[{"award-number":["2308085J03,2208085MF174"]}],"id":[{"id":"10.13039\/501100003995","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,30]]},"DOI":"10.1109\/cec60901.2024.10611963","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:55:15Z","timestamp":1723139715000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Agent Reinforcement Learning with Asymmetric Representation Assisted by Multi-Objective Evolutionary Algorithms"],"prefix":"10.1109","author":[{"given":"Ye","family":"Tian","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Anhui University,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weixin","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Anhui University,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shangshang","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Anhui University,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Panpan","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Anhui University,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Anhui University,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Starcraft II: A new challenge for reinforcement learning","author":"Vinyals","year":"2017","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Optimistic multi-agent policy gradient for cooperative tasks","author":"Zhao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Silver","year":"2014"},{"key":"ref4","article-title":"Evolution-guided policy gradient in reinforcement learning","volume":"31","author":"Khadka","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/11871842_64"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2962137"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2019.10.016"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2022.3186546"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5728"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2022.105875"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3008735"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3470971"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3098186"},{"key":"ref14","first-page":"19490","article-title":"Race: Improve multi-agent reinforcement learning with representation asymmetry and collaborative evolution","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Li","year":"2023"},{"key":"ref15","article-title":"DR3: Value-based deep reinforcement learning requires explicit regularization","author":"Kumar","year":"2021","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Reducing overestimation bias in multi-agent domains using double centralized critics","author":"Ackermann","year":"2019","journal-title":"arXiv preprint"},{"key":"ref17","first-page":"6651","article-title":"Evolutionary reinforcement learning for sample-efficient multiagent coordination","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Majumdar","year":"2020"},{"key":"ref18","article-title":"QD-RL: Efficient mixing of quality and diversity in reinforcement learning","author":"Cideron","year":"2020","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/4235.996017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2014.2308305"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-017-0057-5"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref23","article-title":"Boosting off-policy RL with policy representation and policy-extended value function approximator","volume-title":"ICML Workshop on New Frontiers in Learning, Control, and Dynamical Systems","author":"Zhang","year":"2023"},{"key":"ref24","article-title":"Improving exploration in evolution strategies for deep reinforcement learning via a population of novelty-seeking agents","volume":"31","author":"Conti","year":"2018","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"2024 IEEE Congress on Evolutionary Computation (CEC)","start":{"date-parts":[[2024,6,30]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 IEEE Congress on Evolutionary Computation (CEC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609966\/10611750\/10611963.pdf?arnumber=10611963","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,11]],"date-time":"2024-08-11T04:23:25Z","timestamp":1723350205000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10611963\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/cec60901.2024.10611963","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}