{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T15:19:48Z","timestamp":1759936788118,"version":"3.28.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,9]],"date-time":"2022-10-09T00:00:00Z","timestamp":1665273600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,9]],"date-time":"2022-10-09T00:00:00Z","timestamp":1665273600000},"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":[[2022,10,9]]},"DOI":"10.1109\/smc53654.2022.9945272","type":"proceedings-article","created":{"date-parts":[[2022,11,18]],"date-time":"2022-11-18T15:49:04Z","timestamp":1668786544000},"page":"2709-2714","source":"Crossref","is-referenced-by-count":3,"title":["Sub-optimal Policy Aided Multi-Agent Reinforcement Learning for Flocking Control"],"prefix":"10.1109","author":[{"given":"Yunbo","family":"Qiu","sequence":"first","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yue","family":"Jin","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xudong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3390\/s20164546"},{"key":"ref11","first-page":"305","article-title":"Alvinn: an autonomous land vehicle in a neural network","author":"pomerleau","year":"1988","journal-title":"Proceedings of the 1st International Conference on Neural Information Processing Systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref13","first-page":"465","article-title":"Integrating behavior cloning and reinforcement learning for improved performance in dense and sparse reward environments","author":"goecks","year":"2020","journal-title":"Proc of International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref14","first-page":"1995","article-title":"Coordinated multi-agent imitation learning","author":"le","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref15","first-page":"7472","article-title":"Multi-agent generative adversarial imitation learning","author":"song","year":"2018","journal-title":"Proceedings of the 32Nd International Conference on Neural Information Processing Systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3011211"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.apor.2021.102759"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1357\/1\/012026"},{"key":"ref19","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICUS48101.2019.8995944"},{"key":"ref3","first-page":"401","article-title":"Flocking of multi-agents in constrained environments","volume":"2","author":"sharma","year":"2009","journal-title":"European Journal of Pure and Applied Mathematics"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2944892"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2015.2418871"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2020.103594"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP.2018.8646428"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.3308"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/37401.37406"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3016951"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref20"},{"key":"ref21","first-page":"20 132","article-title":"A minimalist approach to offline reinforcement learning","volume":"34","author":"fujimoto","year":"2021","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","start":{"date-parts":[[2022,10,9]]},"location":"Prague, Czech Republic","end":{"date-parts":[[2022,10,12]]}},"container-title":["2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9945068\/9945069\/09945272.pdf?arnumber=9945272","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,12]],"date-time":"2022-12-12T14:53:17Z","timestamp":1670856797000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9945272\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,9]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/smc53654.2022.9945272","relation":{},"subject":[],"published":{"date-parts":[[2022,10,9]]}}}