{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,11]],"date-time":"2025-07-11T10:35:52Z","timestamp":1752230152966,"version":"3.28.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"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":[[2022,9]]},"DOI":"10.1109\/vtc2022-fall57202.2022.10012835","type":"proceedings-article","created":{"date-parts":[[2023,1,18]],"date-time":"2023-01-18T18:52:20Z","timestamp":1674067940000},"page":"1-7","source":"Crossref","is-referenced-by-count":4,"title":["Sample-Efficient Multi-Agent Reinforcement Learning with Demonstrations for Flocking Control"],"prefix":"10.1109","author":[{"given":"Yunbo","family":"Qiu","sequence":"first","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,Beijing,China"}]},{"given":"Yuzhu","family":"Zhan","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,Beijing,China"}]},{"given":"Yue","family":"Jin","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,Beijing,China"}]},{"given":"Jian","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,Beijing,China"}]},{"given":"Xudong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,Beijing,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/37401.37406"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.2514\/1.G004227"},{"issue":"3","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":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2010.06.014"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3046695"},{"key":"ref6","first-page":"6993","article-title":"Bipartite flock control of multi-agent systems","volume-title":"Proceedings of the 32nd Chinese Control Conference","author":"Fan"},{"key":"ref7","first-page":"6947","article-title":"Flocking with a virtual leader based on distributed event-triggered hybrid control","volume-title":"Proceedings of the 32nd Chinese Control Conference","author":"Yu"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP.2018.8646428"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2020.103594"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCA.2018.8444355"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3016951"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3390\/s20164546"},{"key":"ref13","first-page":"305","article-title":"Alvinn: an autonomous land vehicle in a neural network","volume-title":"Proceedings of the 1st International Conference on Neural Information Processing Systems","author":"Pomerleau"},{"key":"ref14","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume":"8","author":"Ziebart","year":"2008","journal-title":"Aaai"},{"key":"ref15","first-page":"4572","article-title":"Generative adversarial imitation learning","volume-title":"Proceedings of the 30th International Conference on Neural Information Processing Systems","author":"Ho"},{"key":"ref16","first-page":"1995","article-title":"Coordinated multi-agent imitation learning","volume-title":"International Conference on Machine Learning","author":"Le"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2010.65"},{"key":"ref18","first-page":"7472","article-title":"Multi-agent generative adversarial imitation learning","volume-title":"Proceedings of the 32nd International Conference on Neural Information Processing Systems","author":"Song"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref20","first-page":"465","article-title":"Integrating behavior cloning and reinforcement learning for improved performance in dense and sparse reward environments","volume-title":"Proceedings of the 19th International Conference on Autonomous Agents and MultiAgent Systems","author":"Goecks"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref22","first-page":"6382","article-title":"Multiagent actor-critic for mixed cooperative-competitive environments","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","author":"Lowe"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref24","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"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ISIE.2001.931933"}],"event":{"name":"2022 IEEE 96th Vehicular Technology Conference (VTC2022-Fall)","start":{"date-parts":[[2022,9,26]]},"location":"London, United Kingdom","end":{"date-parts":[[2022,9,29]]}},"container-title":["2022 IEEE 96th Vehicular Technology Conference (VTC2022-Fall)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10012685\/10012692\/10012835.pdf?arnumber=10012835","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,9]],"date-time":"2024-02-09T02:54:42Z","timestamp":1707447282000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10012835\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/vtc2022-fall57202.2022.10012835","relation":{},"subject":[],"published":{"date-parts":[[2022,9]]}}}