{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T03:27:07Z","timestamp":1752550027247,"version":"3.40.3"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031268885"},{"type":"electronic","value":"9783031268892"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-26889-2_19","type":"book-chapter","created":{"date-parts":[[2023,2,28]],"date-time":"2023-02-28T16:03:03Z","timestamp":1677600183000},"page":"213-225","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Least-Restrictive Multi-agent Collision Avoidance via\u00a0Deep Meta Reinforcement Learning and\u00a0Optimal Control"],"prefix":"10.1007","author":[{"given":"Salar","family":"Asayesh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mo","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mehran","family":"Mehrandezh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kamal","family":"Gupta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,3,1]]},"reference":[{"issue":"7540","key":"19_CR1","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"issue":"7587","key":"19_CR2","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484\u2013489 (2016)","journal-title":"Nature"},{"key":"19_CR3","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"},{"key":"19_CR4","unstructured":"Schulman, J., Levine, S., Abbeel, P., Jordan, M., Moritz, P.: Trust region policy optimization. In: International Conference on Machine Learning, pp. 1889\u20131897. PMLR (2015)"},{"issue":"4\u20135","key":"19_CR5","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1177\/0278364917710318","volume":"37","author":"S Levine","year":"2018","unstructured":"Levine, S., Pastor, P., Krizhevsky, A., Ibarz, J., Quillen, D.: Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection. Int. J. Robot. Res. 37(4\u20135), 421\u2013436 (2018)","journal-title":"Int. J. Robot. Res."},{"key":"19_CR6","doi-asserted-by":"crossref","unstructured":"Finn, C., Levine, S.: Deep visual foresight for planning robot motion. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 2786\u20132793. IEEE (2017)","DOI":"10.1109\/ICRA.2017.7989324"},{"key":"19_CR7","unstructured":"Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: International Conference on Machine Learning, pp. 1126\u20131135. PMLR (2017)"},{"key":"19_CR8","unstructured":"Duan, Y., Schulman, J., Chen, X., Bartlett, P.L., Sutskever, I., Abbeel, P.: Fast reinforcement learning via slow reinforcement learning. arXiv preprint arXiv:1611.02779 (2016)"},{"key":"19_CR9","unstructured":"Mishra, N., Rohaninejad, M., Chen, X., Abbeel, P.: A simple neural attentive meta-learner. arXiv preprint arXiv:1707.03141 (2017)"},{"issue":"8","key":"19_CR10","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997). https:\/\/doi.org\/10.1162\/neco.1997.9.8.1735","journal-title":"Neural Comput."},{"issue":"7","key":"19_CR11","doi-asserted-by":"publisher","first-page":"947","DOI":"10.1109\/TAC.2005.851439","volume":"50","author":"IM Mitchell","year":"2005","unstructured":"Mitchell, I.M., Bayen, A.M., Tomlin, C.J.: A time-dependent Hamilton-Jacobi formulation of reachable sets for continuous dynamic games. IEEE Trans. Autom. Control 50(7), 947\u2013957 (2005)","journal-title":"IEEE Trans. Autom. Control"},{"issue":"7","key":"19_CR12","doi-asserted-by":"publisher","first-page":"760","DOI":"10.1177\/027836499801700706","volume":"17","author":"P Fiorini","year":"1998","unstructured":"Fiorini, P., Shiller, Z.: Motion planning in dynamic environments using velocity obstacles. Int. J. Robot. Res. 17(7), 760\u2013772 (1998). https:\/\/doi.org\/10.1177\/027836499801700706","journal-title":"Int. J. Robot. Res."},{"key":"19_CR13","doi-asserted-by":"publisher","unstructured":"van den Berg, J., Guy, S.J., Lin, M., Manocha, D.: Reciprocal n-body collision avoidance. In: Pradalier, C., Siegwart, R., Hirzinger, G. (eds.) Robotics Research. Springer Tracts in Advanced Robotics, vol. 70, pp 3\u201319. Springer, Heidelberg (2011). https:\/\/doi.org\/10.1007\/978-3-642-19457-3_1","DOI":"10.1007\/978-3-642-19457-3_1"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"Chen, M., Shih, J.C., Tomlin, C.J.: Multi-vehicle collision avoidance via Hamilton-Jacobi reachability and mixed integer programming. In: 2016 IEEE 55th Conference on Decision and Control (CDC), pp. 1695\u20131700. IEEE (2016)","DOI":"10.1109\/CDC.2016.7798509"},{"key":"19_CR15","doi-asserted-by":"crossref","unstructured":"Chen, Y.F., Liu, M., Everett, M., How, J.P.: Decentralized non-communicating multiagent collision avoidance with deep reinforcement learning. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 285\u2013292. IEEE (2017)","DOI":"10.1109\/ICRA.2017.7989037"},{"issue":"7","key":"19_CR16","doi-asserted-by":"publisher","first-page":"856","DOI":"10.1177\/0278364920916531","volume":"39","author":"T Fan","year":"2020","unstructured":"Fan, T., Long, P., Liu, W., Pan, J.: Distributed multi-robot collision avoidance via deep reinforcement learning for navigation in complex scenarios. Int. J. Robot. Res. 39(7), 856\u2013892 (2020). https:\/\/doi.org\/10.1177\/0278364920916531","journal-title":"Int. J. Robot. Res."},{"key":"19_CR17","doi-asserted-by":"crossref","unstructured":"Everett, M., Chen, Y.F., How, J.P.: Motion planning among dynamic, decision-making agents with deep reinforcement learning. In: 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3052\u20133059. IEEE (2018)","DOI":"10.1109\/IROS.2018.8593871"},{"key":"19_CR18","unstructured":"Shelhamer, E., Mahmoudieh, P., Argus, M., Darrell, T.: Loss is its own reward: self-supervision for reinforcement learning. arXiv preprint arXiv:1612.07307 (2016)"},{"key":"19_CR19","unstructured":"Rakelly, K., Zhou, A., Finn, C., Levine, S., Quillen, D.: Efficient off-policy meta-reinforcement learning via probabilistic context variables. In: International Conference on Machine Learning, pp. 5331\u20135340. PMLR (2019)"},{"key":"19_CR20","unstructured":"Wang, J.X., et al.: Learning to reinforcement learn. arXiv preprint arXiv:1611.05763 (2016)"},{"key":"19_CR21","unstructured":"Sung, F., Zhang, L., Xiang, T., Hospedales, T., Yang, Y.: Learning to learn: meta-critic networks for sample efficient learning. arXiv preprint arXiv:1706.09529 (2017)"},{"key":"19_CR22","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"19_CR23","unstructured":"Kingma, D.P., Welling, M.: Stochastic gradient VB and the variational auto-encoder. In: Second International Conference on Learning Representations (ICLR), vol. 19, p. 121 (2014)"},{"key":"19_CR24","unstructured":"Schulman, J., Moritz, P., Levine, S., Jordan, M., Abbeel, P.: High-dimensional continuous control using generalized advantage estimation. arXiv preprint arXiv:1506.02438 (2015)"},{"key":"19_CR25","doi-asserted-by":"crossref","unstructured":"Van den Berg, J., Lin, M., Manocha, D.: Reciprocal velocity obstacles for real-time multi-agent navigation. In: 2008 IEEE International Conference on Robotics and Automation, pp. 1928\u20131935. IEEE (2008)","DOI":"10.1109\/ROBOT.2008.4543489"}],"container-title":["Lecture Notes in Networks and Systems","Robot Intelligence Technology and Applications 7"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-26889-2_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,28]],"date-time":"2023-02-28T16:05:27Z","timestamp":1677600327000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-26889-2_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031268885","9783031268892"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-26889-2_19","relation":{},"ISSN":["2367-3370","2367-3389"],"issn-type":[{"type":"print","value":"2367-3370"},{"type":"electronic","value":"2367-3389"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"1 March 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"RiTA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Robot Intelligence Technology and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Daejeon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 December 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 December 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"rita2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2022.icrita.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}