{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T12:09:46Z","timestamp":1771330186074,"version":"3.50.1"},"reference-count":23,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"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":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2021,4]]},"DOI":"10.1109\/lra.2021.3068955","type":"journal-article","created":{"date-parts":[[2021,3,25]],"date-time":"2021-03-25T19:58:14Z","timestamp":1616702294000},"page":"4163-4168","source":"Crossref","is-referenced-by-count":32,"title":["Learning to Herd Agents Amongst Obstacles: Training Robust Shepherding Behaviors Using Deep Reinforcement Learning"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6839-7487","authenticated-orcid":false,"given":"Jixuan","family":"Zhi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0840-6131","authenticated-orcid":false,"given":"Jyh-Ming","family":"Lien","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TENCON.2016.7848636"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139438"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.3390\/s17122729","article-title":"Autonomous shepherding behaviors of multiple target steering robots","volume":"17","author":"lee","year":"2017","journal-title":"SENSORS"},{"key":"ref13","article-title":"Learning shepherding behavior","author":"baumann","year":"2015"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref15","first-page":"658","article-title":"A deep hierarchical reinforcement learner for aerial shepherding of ground swarms","author":"nguyen","year":"0","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref16","volume":"21","author":"reynolds","year":"1987","journal-title":"Flocks Herds and Schools A Distributed Behavioral Model"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref18","article-title":"Prioritized experience replay","author":"schaul","year":"2015"},{"key":"ref19","first-page":"2094","article-title":"Deep reinforcement learning with double q-learning","author":"van hasselt","year":"0","journal-title":"Proc 13th AAAI Conf Artif Intell"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2018.2853610"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MILCOM.2007.4455059"},{"key":"ref6","first-page":"3402","article-title":"Shepherding behaviors with multiple shepherds","author":"lien","year":"0","journal-title":"Proc IEEE Int Conf Robot Automat"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-4-431-35873-2_24"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-16958-8_21"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2009.5354032"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IRC.2017.51"},{"key":"ref1","first-page":"4159","article-title":"Shepherding behaviors","author":"lien","year":"0","journal-title":"Proc IEEE Int Conf Robot Automat"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1098\/rsif.2014.0719"},{"key":"ref20","first-page":"864","article-title":"Investigating contingency awareness using atari 2600 games","author":"bellemare","year":"0","journal-title":"Proc 26th AAAI Conf Artif Intell"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/70.508439"},{"key":"ref21","article-title":"Learning to herd agents amongst obstacles: Training robust shepherding behaviors using deep reinforcement learning","author":"zhi","year":"2020"},{"key":"ref23","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9285111\/09387150.pdf?arnumber=9387150","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:54:29Z","timestamp":1652194469000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9387150\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4]]},"references-count":23,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/lra.2021.3068955","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4]]}}}