{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T07:49:20Z","timestamp":1760168960896,"version":"3.28.0"},"reference-count":34,"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\/ijcnn54540.2023.10191313","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":2,"title":["Evolution Strategies Enhanced Complex Multiagent Coordination"],"prefix":"10.1109","author":[{"given":"Yunfei","family":"Du","sequence":"first","affiliation":[{"name":"Hikvision Research Institude,Hangzhou,China,310051"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yin","family":"Wang","sequence":"additional","affiliation":[{"name":"Hikvision Research Institude,Hangzhou,China,310051"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ya","family":"Cong","sequence":"additional","affiliation":[{"name":"Hikvision Research Institude,Hangzhou,China,310051"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weihao","family":"Jiang","sequence":"additional","affiliation":[{"name":"Hikvision Research Institude,Hangzhou,China,310051"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiliang","family":"Pu","sequence":"additional","affiliation":[{"name":"Hikvision Research Institude,Hangzhou,China,310051"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"6860","article-title":"Coach-player multi-agent reinforcement learning for dynamic team composition","author":"liu","year":"2021","journal-title":"In International Conference on Machine Learning"},{"key":"ref12","article-title":"Social influence as intrinsic motivation for multi-agent deep reinforcement learning","author":"jaques","year":"2018","journal-title":"In International Conference on Machine Learning"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759651"},{"key":"ref15","article-title":"Episodic multi-agent reinforcement learning with curiosity-driven exploration","author":"zheng","year":"2021","journal-title":"In Neural Information Processing Systems"},{"key":"ref14","first-page":"10053","article-title":"Learning multi-agent coordination for enhancing target coverage in directional sensor networks","volume":"33","author":"xu","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3387168.3387199"},{"key":"ref30","first-page":"6651","article-title":"Evolutionary reinforcement learning for sample-efficient multiagent coordination","author":"majumdar","year":"2020","journal-title":"In International Conference on Machine Learning"},{"key":"ref11","article-title":"Ligs: Learnable intrinsic-reward generation selection for multi-agent learning","volume":"abs 2112 2618","author":"mguni","year":"2021","journal-title":"ArXiv"},{"key":"ref33","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":"ref10","article-title":"Maven: Multi-agent variational exploration","author":"mahajan","year":"2019","journal-title":"In Neural Information Processing Systems"},{"key":"ref32","article-title":"Reducing overes-timation bias in multi-agent domains using double centralized critics","author":"ackermann","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref2","article-title":"Deep multi agent re-inforcement learning for autonomous driving","author":"bhalla","year":"2020","journal-title":"Canadian Conference on AI"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOMWKSHPS54753.2022.9798273"},{"key":"ref17","article-title":"Deep reinforcement learning versus evolution strategies: A comparative survey","author":"majid","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref16","first-page":"4992","article-title":"The emergence of individuality","author":"jiang","year":"2021","journal-title":"In International Conference on Machine Learning"},{"key":"ref19","article-title":"Emergent complexity via multi-agent competition","author":"bansal","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref18","article-title":"Coordinated exploration via intrinsic rewards for multi-agent reinforcement learning","author":"iqbal","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"3283","DOI":"10.1609\/aaai.v34i04.5728","article-title":"Proximal distilled evolutionary rein-forcement learning","volume":"34","author":"bodnar","year":"2020","journal-title":"In Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref23","first-page":"3341","article-title":"Collaborative evolutionary reinforcement learning","author":"khadka","year":"2019","journal-title":"In International Conference on Machine Learning"},{"key":"ref26","first-page":"1237","article-title":"Off-policy evolutionary reinforcement learning with maximum mutations","author":"suri","year":"2022","journal-title":"Proc of International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref25","article-title":"Cem-rl: Combining evolutionary and gradient-based methods for policy search","author":"pourchot","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref20","volume":"259","author":"butz","year":"2006","journal-title":"Rule-Based Evolutionary Online Learning Systems"},{"key":"ref22","article-title":"Evolution-guided policy gradient in reinforcement learning","volume":"31","author":"khadka","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1177\/105971239200100104"},{"key":"ref28","article-title":"Evolution strategies as a scalable alternative to reinforcement learning","author":"salimans","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref27","article-title":"Deep neuroevolution: Genetic algorithms are a competitive alternative for training deep neural networks for reinforcement learning","author":"such","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3449726.3459576"},{"key":"ref8","article-title":"Qplex: Duplex dueling multi-agent q-learning","volume":"abs 2008 1062","author":"wang","year":"2020","journal-title":"ArXiv"},{"key":"ref7","first-page":"4295","article-title":"Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning","author":"rashid","year":"2018","journal-title":"In International Conference on Machine Learning"},{"key":"ref9","first-page":"5887","article-title":"Qtran: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","author":"son","year":"2019","journal-title":"In International Conference on Machine Learning"},{"key":"ref4","first-page":"479","article-title":"Ha-light: Hierarchical deep reinforcement learning for cooperative arterial traffic signal control with cycle strategy","author":"zeng","year":"2022","journal-title":"2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITS C)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3150151"},{"key":"ref6","article-title":"Emergent tool use from multi-agent autocurricula","volume":"abs 1909 7528","author":"baker","year":"2019","journal-title":"ArXiv"},{"key":"ref5","first-page":"621","article-title":"Towards playing full moba games with deep reinforcement learning","volume":"33","author":"ye","year":"2020","journal-title":"Advances in neural information processing systems"}],"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\/10191313.pdf?arnumber=10191313","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T17:42:07Z","timestamp":1692639727000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10191313\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,18]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/ijcnn54540.2023.10191313","relation":{},"subject":[],"published":{"date-parts":[[2023,6,18]]}}}