{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T20:15:58Z","timestamp":1775592958051,"version":"3.50.1"},"publisher-location":"Berlin, Heidelberg","reference-count":11,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783540497196","type":"print"},{"value":"9783540497202","type":"electronic"}],"license":[{"start":{"date-parts":[[2007,1,1]],"date-time":"2007-01-01T00:00:00Z","timestamp":1167609600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2007]]},"DOI":"10.1007\/978-3-540-49720-2_6","type":"book-chapter","created":{"date-parts":[[2007,4,21]],"date-time":"2007-04-21T21:29:51Z","timestamp":1177190991000},"page":"121-135","source":"Crossref","is-referenced-by-count":12,"title":["Reinforcement Learning for Autonomous Robotic Fish"],"prefix":"10.1007","author":[{"given":"Jindong","family":"Liu","sequence":"first","affiliation":[]},{"given":"Lynne E.","family":"Parker","sequence":"additional","affiliation":[]},{"given":"Raj","family":"Madhavan","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"6_CR1_6","unstructured":"http:\/\/www.gumstix.org ."},{"key":"6_CR2_6","unstructured":"L. C. Barid and A. W. Moore. Gradient descent for general reinforcement learning. In Proceedings of the International Conference on Advances in neural information processing systems II, pages 968-974. MIT Press, 1999."},{"key":"6_CR3_6","doi-asserted-by":"crossref","unstructured":"G. Z. Grudic, V. Kumar, and L. Ungar. Using policy gradient reinfrocement learning on autonmous robot controllers. In Proceedings of IEEE\/RSJ Interna-tional Conference on Intelligent Robots and Systems, pages 406-411, Las Vagas, Navada, USA, Oct 2003.","DOI":"10.1109\/IROS.2003.1250662"},{"key":"6_CR4_6","doi-asserted-by":"crossref","unstructured":"G. Hornby, S. Takamura, J. Yokono, O. Hanagata, T. Yamamoto, and M. Fujita. Evolving robust gaits with AIBO. In Proceedings of IEEE International Con-ference on Robotics and Automation, pages 3040-3045, 2000.","DOI":"10.1109\/ROBOT.2000.846489"},{"key":"6_CR5_6","doi-asserted-by":"crossref","unstructured":"N. Kohl and P. Stone. Policy gradient reinforcement learning for fast quadrupedal locomotion. In Proceedings of IEEE International Conference on Robotics and Automation, volume 3, pages 2619-2624, May 2004.","DOI":"10.1109\/ROBOT.2004.1307456"},{"key":"6_CR6_6","unstructured":"J. Liu and H. Hu. Building a 3d simulator for autonomous navigation of robotic fishes. In Proceedings of IEEE\/RSJ International Conference on Intelligent Robots and Systems, pages 613-618, Sendai, Japan, Oct 2004."},{"key":"6_CR7_6","unstructured":"J. Liu and H. Hu. Mimicry of sharp turning behaviours in a robotic fish. In Pro-ceedings of IEEE International Conference on Robotics and Automation, pages 3329-3334, Barcelona, Spain, April 2005."},{"key":"6_CR8_6","unstructured":"L. Peshkin, K. Kim, N. Meuleau, and L. Kaelbling. Learning to cooperate via policy search. In Proceedings of the 6th International Conference on Uncertainty in Artificial Intelligence, pages 307-314, 2000."},{"key":"6_CR9_6","unstructured":"C. J. C. H. Watkins. Learning from Delayed Rewards. PhD thesis, Cambridge University, 1989."},{"key":"6_CR10_6","first-page":"229","volume":"8","author":"RJ William","year":"1992","unstructured":"R. J. William. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine learning, 8:229-256, 1992.","journal-title":"Machine learning"},{"key":"6_CR11_6","unstructured":"R. Zhang and P. Vadakkepat. An evolutionary algorithm for trajectory based gait generation of biped robot. In Proceedings of the International Conference on Computational Intelligence, Robotics and Autonomous Systems, Singapore, 2003."}],"container-title":["Studies in Computational Intelligence","Mobile Robots: The Evolutionary Approach"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-49720-2_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T21:38:22Z","timestamp":1736977102000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-49720-2_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007]]},"ISBN":["9783540497196","9783540497202"],"references-count":11,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-49720-2_6","relation":{},"ISSN":["1860-949X","1860-9503"],"issn-type":[{"value":"1860-949X","type":"print"},{"value":"1860-9503","type":"electronic"}],"subject":[],"published":{"date-parts":[[2007]]}}}