{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T01:20:53Z","timestamp":1774315253588,"version":"3.50.1"},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"3-4","license":[{"start":{"date-parts":[[2010,5,18]],"date-time":"2010-05-18T00:00:00Z","timestamp":1274140800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Intell Robot Syst"],"published-print":{"date-parts":[[2010,12]]},"DOI":"10.1007\/s10846-010-9429-4","type":"journal-article","created":{"date-parts":[[2010,5,17]],"date-time":"2010-05-17T04:03:23Z","timestamp":1274069003000},"page":"531-551","source":"Crossref","is-referenced-by-count":24,"title":["Distributed Reinforcement Learning for Coordinate Multi-Robot Foraging"],"prefix":"10.1007","volume":"60","author":[{"given":"Hongliang","family":"Guo","sequence":"first","affiliation":[]},{"given":"Yan","family":"Meng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2010,5,18]]},"reference":[{"key":"9429_CR1","unstructured":"Agogino, A.K., Tumer, K.: QUICR-learning for multi-agent coordination. In: Proceedings of the 21st National Conference on Artificial Intelligence, Boston, MA (2006)"},{"issue":"6","key":"9429_CR2","doi-asserted-by":"crossref","first-page":"926","DOI":"10.1109\/70.736776","volume":"14","author":"T Balch","year":"1998","unstructured":"Balch, T., Arkin, R.C.: Behavior-based formation control for multi-agent teams. IEEE Trans. Robot Autom. 14(6), 926\u2013939 (1998)","journal-title":"IEEE Trans. Robot Autom."},{"issue":"1","key":"9429_CR3","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1007\/BF00735341","volume":"1","author":"T Balch","year":"1995","unstructured":"Balch, T., Arkin, R.C.: Communication in reactive multiagent robotics systems. Auton. Robots 1(1), 27\u201352 (1995)","journal-title":"Auton. Robots"},{"key":"9429_CR4","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1023\/A:1022140919877","volume":"13","author":"AG Barto","year":"2003","unstructured":"Barto, A.G., Mahadevan, S.: Recent advances in hierarchical reinforcement learning. Discret. Event Dyn. Syst. 13, 41\u201377 (2003)","journal-title":"Discret. Event Dyn. Syst."},{"key":"9429_CR5","volume-title":"Dynamic Programming and Optimal Control","author":"DP Bertsekas","year":"2001","unstructured":"Bertsekas, D.P.: Dynamic Programming and Optimal Control. Athena Scientific, Nashua (2001)"},{"key":"9429_CR6","unstructured":"Coggan, M.: Exploration and exploitation in reinforcement learning. In: Fourth International Conference on Computational Intelligence and Multimedia Applications (ICCIMA\u201901). Shonan International Village Yokosuka City (2001)"},{"key":"9429_CR7","unstructured":"Greenwald, A., Hall, K.: Correlated-Q learning. In: Proceedings of the 20th International Conference on Machine Learning (ICML 2003). Washington DC, USA (2003)"},{"key":"9429_CR8","unstructured":"Guo, H., Meng, Y.: Dynamic correlation matrix based multi-Q learning for a multi-robot system. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS 08). Nice, France (2008)"},{"key":"9429_CR9","doi-asserted-by":"crossref","unstructured":"Kapetanakis, S., Kudenko, D.: Reinforcement learning of coordination in heterogeneous cooperative multi-agent systems. In: Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems. Columbia University in New York City (2004)","DOI":"10.1007\/978-3-540-32274-0_8"},{"key":"9429_CR10","doi-asserted-by":"crossref","unstructured":"Littman, M.L.: Markov games as a framework for multi-agent reinforcement learning. In: Proceedings of the Eleventh International Conference on Machine Learning, pp. 157\u2013163. New Brunswick, NJ, USA (1994)","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"9429_CR11","unstructured":"Littman, M.L.: Friend-or-foe Q-learning in general-sum games. In: Proceedings of the 18th International Conference on Machine Learning, Williams College(Massachusetts) USA Morgan Kaufman, pp. 322\u2013328 (2001)"},{"key":"9429_CR12","doi-asserted-by":"crossref","unstructured":"Marsella, S., Adibi, J., Al-Onaizan, Y., Kaminka, G., Muslea, I., Tambe, M.: On being a teammate: experiences acquired in the design of RoboCup teams. In: Etzioni, O., Muller, J., Bradshaw, J. (eds.) Proceedings of the Third Annual Conference on Autonomous Agents, pp. 221\u2013227 (1999)","DOI":"10.1145\/301136.301199"},{"key":"9429_CR13","doi-asserted-by":"crossref","unstructured":"Matignon, L., Laurent, G.J., Fort-Piat, N.L.: Hysteretic Q-learning: an algorithm for decentralized reinforcement learning in cooperative multi-agent teams. In: 2007 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS07). San Diego, CA, USA (2007)","DOI":"10.1109\/IROS.2007.4399095"},{"key":"9429_CR14","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1016\/S0921-8890(99)00038-X","volume":"29","author":"A Martinoli","year":"1999","unstructured":"Martinoli, A., Ijspeert, A., Mondada, F.: Understanding collective aggregation mechanisms: from probabilistic modeling to experiments with real agents. Robot. Auton. Syst. 29, 51\u201363 (1999)","journal-title":"Robot. Auton. Syst."},{"key":"9429_CR15","unstructured":"McLurkin, J., Smith, J.: Distributed algorithms for dispersion in indoor environments using a swarm of autonomous mobile robots. In: Symposium on Distributed Autonomous Robotic Systems, Springer (2004)"},{"key":"9429_CR16","unstructured":"Meng, X., Babuska, R., Busoniu, L., Chen, Y., Tan, W.: An improved multiagent reinforcement learning algorithm. In: Proceedings of the IEEE\/WIC\/ACM International Conference on Intelligent Agent Technology\u2014Volume 00 Compiegne University of Technology, France, pp. 337\u2013343 (2005)"},{"key":"9429_CR17","doi-asserted-by":"crossref","unstructured":"Meng, Y., Gan, J.: LIVS: local interaction via virtual stigmergy coordination in distributed search and collective cleanup. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems, San Diego, CA, USA (2007)","DOI":"10.1109\/IROS.2007.4399254"},{"key":"9429_CR18","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/2889.001.0001","volume-title":"Evolutionary Robotics: the Biology, Intelligence, and Technology of Self-organizing Machines","author":"S Nolfi","year":"2000","unstructured":"Nolfi, S., Floreano, D.: Evolutionary Robotics: the Biology, Intelligence, and Technology of Self-organizing Machines. MIT, Cambridge (2000)"},{"issue":"2","key":"9429_CR19","first-page":"5","volume":"2","author":"LE Parker","year":"2008","unstructured":"Parker, L.E.: Distributed intelligence: overview of the field and its application in multi-robot systems. Invited article. Journal of Physical Agents 2(2), 5\u201314 (2008) (special issue on multi-robot systems)","journal-title":"Invited article. Journal of Physical Agents"},{"key":"9429_CR20","volume-title":"Reinforcement Learning: an Introduction","author":"S Sutton","year":"1998","unstructured":"Sutton, S., Barto, G.: Reinforcement Learning: an Introduction. MIT, Cambridge (1998)"},{"key":"9429_CR21","doi-asserted-by":"crossref","unstructured":"Suematsu, N., Hayashi, A.: A multiagent reinforcement learning algorithm using extended optimal response. In: Proceedings of the First International Joint Conference on Autonomous Agents and Multiagent Systems: Part 1. Bologna, Italy (2002)","DOI":"10.1145\/544741.544831"},{"key":"9429_CR22","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1613\/jair.433","volume":"7","author":"M Tambe","year":"1997","unstructured":"Tambe, M.: Towards flexible teamwork. J. Artif. Intell. Res. 7, 83\u2013124 (1997)","journal-title":"J. Artif. Intell. Res."},{"key":"9429_CR23","first-page":"279","volume":"8","author":"CJ Watkins","year":"1992","unstructured":"Watkins, C.J., Dayan, P.: Q-learning. Mach. Learn. 8, 279\u2013292 (1992)","journal-title":"Mach. Learn."},{"key":"9429_CR24","volume-title":"Matrix Analysis and Applications","author":"X Zhang","year":"2004","unstructured":"Zhang, X.: Matrix Analysis and Applications. Tsinghua University Press, Beijing (2004) ISBN 7-302-09271-0\/0.390"},{"key":"9429_CR25","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Meng, Y.: Adaptive object tracking using particle swarm optimization. In: IEEE International Symposium on Computational Intelligence in Robotics and Automation, Jacksonville, Florida, USA (2007)","DOI":"10.1109\/CIRA.2007.382848"},{"issue":"1","key":"9429_CR26","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1177\/0278364906061160","volume":"25","author":"R Zlot","year":"2006","unstructured":"Zlot, R., Stentz, A.: Market-based multirobot coordination for complex tasks. Int. J. Rob. Res. 25(1), 73\u2013101 (2006)","journal-title":"Int. J. Rob. Res."}],"container-title":["Journal of Intelligent & Robotic Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10846-010-9429-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10846-010-9429-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10846-010-9429-4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T22:08:21Z","timestamp":1740089301000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10846-010-9429-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,5,18]]},"references-count":26,"journal-issue":{"issue":"3-4","published-print":{"date-parts":[[2010,12]]}},"alternative-id":["9429"],"URL":"https:\/\/doi.org\/10.1007\/s10846-010-9429-4","relation":{},"ISSN":["0921-0296","1573-0409"],"issn-type":[{"value":"0921-0296","type":"print"},{"value":"1573-0409","type":"electronic"}],"subject":[],"published":{"date-parts":[[2010,5,18]]}}}