{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T06:11:36Z","timestamp":1742969496100,"version":"3.40.3"},"publisher-location":"Cham","reference-count":16,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030927899"},{"type":"electronic","value":"9783030927905"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-030-92790-5_31","type":"book-chapter","created":{"date-parts":[[2022,1,3]],"date-time":"2022-01-03T16:14:54Z","timestamp":1641226494000},"page":"401-414","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Using Reinforcement Learning to\u00a0Herd a\u00a0Robotic Swarm to\u00a0a\u00a0Target Distribution"],"prefix":"10.1007","author":[{"given":"Zahi","family":"Kakish","sequence":"first","affiliation":[]},{"given":"Karthik","family":"Elamvazhuthi","sequence":"additional","affiliation":[]},{"given":"Spring","family":"Berman","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,1,3]]},"reference":[{"key":"31_CR1","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018)"},{"issue":"8","key":"31_CR2","doi-asserted-by":"publisher","first-page":"1972","DOI":"10.1109\/TAC.2008.930098","volume":"53","author":"M Ji","year":"2008","unstructured":"Ji, M., Ferrari-Trecate, G., Egerstedt, M., Buffa, A.: Containment control in mobile networks. IEEE Trans. Autom. Control 53(8), 1972\u20131975 (2008)","journal-title":"IEEE Trans. Autom. Control"},{"key":"31_CR3","doi-asserted-by":"publisher","DOI":"10.1515\/9781400835355","volume-title":"Graph Theoretic Methods in Multiagent Networks","author":"M Mesbahi","year":"2010","unstructured":"Mesbahi, M., Egerstedt, M.: Graph Theoretic Methods in Multiagent Networks. Princeton University Press, Princeton (2010)"},{"issue":"2","key":"31_CR4","doi-asserted-by":"publisher","first-page":"517","DOI":"10.1109\/TRO.2017.2776308","volume":"34","author":"A Pierson","year":"2017","unstructured":"Pierson, A., Schwager, M.: Controlling noncooperative herds with robotic herders. IEEE Trans. Rob. 34(2), 517\u2013525 (2017)","journal-title":"IEEE Trans. Rob."},{"key":"31_CR5","doi-asserted-by":"crossref","unstructured":"Elamvazhuthi, K., Wilson, S., Berman, S.: Confinement control of double integrators using partially periodic leader trajectories. In: American Control Conference, pp. 5537\u20135544 (2016)","DOI":"10.1109\/ACC.2016.7526538"},{"issue":"4","key":"31_CR6","doi-asserted-by":"publisher","first-page":"901","DOI":"10.1109\/TRO.2018.2853610","volume":"34","author":"AA Paranjape","year":"2018","unstructured":"Paranjape, A.A., Chung, S.-J., Kim, K., Shim, D.H.: Robotic herding of a flock of birds using an unmanned aerial vehicle. IEEE Trans. Robot. 34(4), 901\u2013915 (2018)","journal-title":"IEEE Trans. Robot."},{"key":"31_CR7","doi-asserted-by":"crossref","unstructured":"Go, C.K., Lao, B., Yoshimoto, J., Ikeda, K.: A reinforcement learning approach to the shepherding task using SARSA. In: International Joint Conference on Neural Networks, pp. 3833\u20133836 (2016)","DOI":"10.1109\/IJCNN.2016.7727694"},{"issue":"1","key":"31_CR8","doi-asserted-by":"publisher","first-page":"015001","DOI":"10.1088\/1748-3190\/ab49a4","volume":"15","author":"K Elamvazhuthi","year":"2019","unstructured":"Elamvazhuthi, K., Berman, S.: Mean-field models in swarm robotics: a survey. Bioinspiration Biomimetics 15(1), 015001 (2019)","journal-title":"Bioinspiration Biomimetics"},{"issue":"1","key":"31_CR9","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1007\/s11721-017-0142-9","volume":"12","author":"A \u0160o\u0161i\u0107","year":"2017","unstructured":"\u0160o\u0161i\u0107, A., Zoubir, A.M., Koeppl, H.: Reinforcement learning in a continuum of agents. Swarm Intell. 12(1), 23\u201351 (2017). https:\/\/doi.org\/10.1007\/s11721-017-0142-9","journal-title":"Swarm Intell."},{"issue":"54","key":"31_CR10","first-page":"1","volume":"20","author":"M H\u00fcttenrauch","year":"2019","unstructured":"H\u00fcttenrauch, M., Adrian, S., Neumann, G.: Deep reinforcement learning for swarm systems. J. Mach. Learn. Res. 20(54), 1\u201331 (2019)","journal-title":"J. Mach. Learn. Res."},{"key":"31_CR11","unstructured":"Yang, Y., Luo, R., Li, M., Zhou, M., Zhang, W., Wang, J.: Mean field multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 5567\u20135576 (2018)"},{"key":"31_CR12","unstructured":"Brockman, G., et al.: OpenAI Gym. arXiv preprint arXiv:1606.01540 (2016)"},{"key":"31_CR13","unstructured":"Kakish, Z.: Herding OpenAI Gym Environment (2019). https:\/\/github.com\/acslaboratory\/gym-herding"},{"issue":"1","key":"31_CR14","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1109\/MCS.2019.2949973","volume":"40","author":"S Wilson","year":"2020","unstructured":"Wilson, S., Glotfelter, P., Wang, L., Mayya, S., Notomista, G., Mote, M., Egerstedt, M.: The Robotarium: globally impactful opportunities, challenges, and lessons learned in remote-access, distributed control of multirobot systems. IEEE Control Syst. Mag. 40(1), 26\u201344 (2020)","journal-title":"IEEE Control Syst. Mag."},{"issue":"3","key":"31_CR15","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1109\/TRO.2017.2659727","volume":"33","author":"L Wang","year":"2017","unstructured":"Wang, L., Ames, A.D., Egerstedt, M.: Safety barrier certificates for collisions-free multirobot systems. IEEE Trans. Rob. 33(3), 661\u2013674 (2017)","journal-title":"IEEE Trans. Rob."},{"key":"31_CR16","unstructured":"Kakish, Z., Elamvazhuthi, K., Berman, S.: Using reinforcement learning to herd a robotic swarm to a target distribution. Autonomous Collective Systems Laboratory YouTube Channel (2020). https:\/\/youtu.be\/py3Pe24YDjE"}],"container-title":["Springer Proceedings in Advanced Robotics","Distributed Autonomous Robotic Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-92790-5_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,8]],"date-time":"2022-05-08T02:42:21Z","timestamp":1651977741000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-92790-5_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783030927899","9783030927905"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-92790-5_31","relation":{},"ISSN":["2511-1256","2511-1264"],"issn-type":[{"type":"print","value":"2511-1256"},{"type":"electronic","value":"2511-1264"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"3 January 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DARS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium Distributed Autonomous Robotic Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kyoto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 June 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 June 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dars2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}