{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T10:11:01Z","timestamp":1783937461643,"version":"3.55.0"},"reference-count":20,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,6]]},"DOI":"10.1109\/icca.2018.8444355","type":"proceedings-article","created":{"date-parts":[[2018,9,7]],"date-time":"2018-09-07T14:50:55Z","timestamp":1536331855000},"page":"306-311","source":"Crossref","is-referenced-by-count":25,"title":["Multi-vehicle Flocking Control with Deep Deterministic Policy Gradient Method"],"prefix":"10.1109","author":[{"given":"Zhao","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Lyu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Quan","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinwen","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunhui","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuai","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Cooperative and distributed reinforcement learning of drones for field coverage","author":"pham","year":"2018","journal-title":"arXiv preprint arXiv 1803 07250"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2014.2312392"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2509646"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2651371"},{"key":"ref14","first-page":"1928","article-title":"Reciprocal velocity obstacles for real-time multi-agent navigation","author":"berg","year":"2008","journal-title":"IEEE International Conference on Robotics and Automation"},{"key":"ref15","article-title":"Multi-agent actor-critic for mixed cooperativecompetitive environments","volume":"abs 1706 2275","author":"lowe","year":"2017","journal-title":"CoRR"},{"key":"ref16","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"},{"key":"ref17","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"Computer Science"},{"key":"ref18","first-page":"265","article-title":"Tensorflow: A system for large-scale machine learning","volume":"16","author":"abadi","year":"2016","journal-title":"OSDI"},{"key":"ref19","article-title":"Openai gym","author":"brockman","year":"2016","journal-title":"arXiv preprint arXiv 1606 01540"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-23778-7_57"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21597"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2005.864190"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/87.960341"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989037"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1109\/TNN.2004.842673","article-title":"Reinforcement learning: An introduction, bradford book","volume":"16","author":"sutton","year":"2005","journal-title":"IEEE Transactions on Neural Networks"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917719333"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1109\/MCS.2007.338264","article-title":"Information consensus in multivehicle cooperative control","volume":"27","author":"ren","year":"2007","journal-title":"IEEE Control Systems"},{"key":"ref9","first-page":"2137","article-title":"Learning to communicate with deep multi-agent reinforcement learning","author":"foerster","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref20","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"Neural Information Processing Systems (NIPS)"}],"event":{"name":"2018 IEEE 14th International Conference on Control and Automation (ICCA)","location":"Anchorage, AK","start":{"date-parts":[[2018,6,12]]},"end":{"date-parts":[[2018,6,15]]}},"container-title":["2018 IEEE 14th International Conference on Control and Automation (ICCA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8409887\/8444139\/08444355.pdf?arnumber=8444355","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T00:15:41Z","timestamp":1598228141000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8444355\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icca.2018.8444355","relation":{},"subject":[],"published":{"date-parts":[[2018,6]]}}}