{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T14:47:22Z","timestamp":1770821242249,"version":"3.50.1"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2010,2,4]],"date-time":"2010-02-04T00:00:00Z","timestamp":1265241600000},"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":[[2010,8]]},"DOI":"10.1007\/s10846-010-9396-9","type":"journal-article","created":{"date-parts":[[2010,2,3]],"date-time":"2010-02-03T09:18:42Z","timestamp":1265188722000},"page":"145-166","source":"Crossref","is-referenced-by-count":15,"title":["Designing Decentralized Controllers for Distributed-Air-Jet MEMS-Based Micromanipulators by Reinforcement Learning"],"prefix":"10.1007","volume":"59","author":[{"given":"La\u00ebtitia","family":"Matignon","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guillaume J.","family":"Laurent","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nadine","family":"Le Fort-Piat","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yves-Andr\u00e9","family":"Chapuis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2010,2,4]]},"reference":[{"key":"9396_CR1","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1109\/TMECH.2008.2004770","volume":"14","author":"M Ataka","year":"2009","unstructured":"Ataka, M., Legrand, B., Buchaillot, L., Collard, D., Fujita, H.: Design, fabrication and operation of two dimensional conveyance system with ciliary actuator arrays. IEEE\/ASME Trans. Mechatron. 14, 119\u2013125 (2009)","journal-title":"IEEE\/ASME Trans. Mechatron"},{"issue":"4","key":"9396_CR2","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1109\/84.273089","volume":"2","author":"M Ataka","year":"1994","unstructured":"Ataka, M., Omodaka, A., Takeshima, N., Fujita, H.: Fabrication and operation of polyimide bimorph actuators for a ciliar motion system. IEEE\/ASME J. Microelectromech. Syst. 2(4), 146\u2013150 (1994)","journal-title":"IEEE\/ASME J. Microelectromech. Syst."},{"issue":"2","key":"9396_CR3","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1109\/70.843172","volume":"16","author":"KF B\u00f6hringer","year":"2000","unstructured":"B\u00f6hringer, K.F., Donald, B.R., Kavraki, L., Lamiraux, F.: Part orientation with one or two stable equilibria using programmable vector fields. IEEE Trans. Robot. Autom. 16(2), 157\u2013170 (2000)","journal-title":"IEEE Trans. Robot. Autom."},{"key":"9396_CR4","first-page":"255","volume-title":"Algorithms for Robotic Motion and Manipulation","author":"KF B\u00f6hringer","year":"1997","unstructured":"B\u00f6hringer, K.F., Donald, B.R., MacDonald, N.C.: Upper and lower bounds for programmable vector fields with applications to MEMS and vibratory plate parts feeders. In: Laumond, J.-P., Overmars M. (eds.) Algorithms for Robotic Motion and Manipulation, pp. 255\u2013276. AK Peters, Wellesley, MA, USA (1997)"},{"key":"9396_CR5","doi-asserted-by":"crossref","unstructured":"B\u00f6hringer, K.F., Donald, B.R., Mihailovich, R., MacDonald, N.C.: Sensorless manipulation using massively parallel microfabricated actuator arrays. In: Proc. of the IEEE Int. Conf. on Robotics and Automation, pp.\u00a0826\u2013833. San Diego, CA (1994)","DOI":"10.1109\/ROBOT.1994.351386"},{"key":"9396_CR6","doi-asserted-by":"crossref","unstructured":"B\u00f6hringer, K.F., Randall, B., Noel, D., Macdonald, C.: What programmable vector fields can (and cannot) do: force field algorithms for mems and vibratory parts feeders. In: Proc. of the IEEE Int. Conf. on Robotics and Automation, pp.\u00a0822\u2013829 (1996)","DOI":"10.1109\/ROBOT.1996.503875"},{"issue":"2","key":"9396_CR7","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1109\/TSMCC.2007.913919","volume":"38","author":"L Busoniu","year":"2008","unstructured":"Busoniu, L., Babuska, R., De\u00a0Schutter, B.: A comprehensive survey of multiagent reinforcement learning. IEEE Trans. Syst. Man Cybern., Part C Appl. Rev. 38(2), 156\u2013172 (2008)","journal-title":"IEEE Trans. Syst. Man Cybern., Part C Appl. Rev."},{"key":"9396_CR8","doi-asserted-by":"crossref","unstructured":"Busoniu, L., Babuska, R., Schutter, B.D.: Decentralized reinforcement learning control of a robotic manipulator. In: Proceedings of the 9th International Conference on Control, Automation, Robotics and Vision (ICARCV 2006), pp.\u00a01347\u20131352. Singapore (2006)","DOI":"10.1109\/ICARCV.2006.345351"},{"issue":"4","key":"9396_CR9","doi-asserted-by":"crossref","first-page":"1926","DOI":"10.1109\/TIE.2007.898297","volume":"54","author":"YA Chapuis","year":"2007","unstructured":"Chapuis, Y.A., Zhou, L., Fukuta, Y., Mita, Y., Fujita, H.: Fpga-based decentralized control of arrayed mems for microrobotic application. IEEE Trans. Ind. Electron. 54(4), 1926\u20131936 (2007)","journal-title":"IEEE Trans. Ind. Electron."},{"key":"9396_CR10","unstructured":"Claus, C., Boutilier, C.: The dynamics of reinforcement learning in cooperative multiagent systems. In: Proceedings of the Fifteenth National Conference on Artificial Intelligence, pp.\u00a0746\u2013752 (1998)"},{"key":"9396_CR11","doi-asserted-by":"crossref","unstructured":"Elfwing, S., Uchibe, E., Doya, K., Christensen, H.I.: Multi-agent reinforcement learning: using macro actions to learn a mating task. In: Proceedings of ICRA (2004)","DOI":"10.1109\/IROS.2004.1389904"},{"issue":"4","key":"9396_CR12","doi-asserted-by":"crossref","first-page":"912","DOI":"10.1109\/JMEMS.2006.879378","volume":"15","author":"Y Fukuta","year":"2006","unstructured":"Fukuta, Y., Chapuis, Y.A., Mita, Y., Fujita, H.: Design, fabrication and control of mems-based actuator arrays for air-flow distributed micromanipulation. IEEE\/ASME J. Microelectromech. Syst. 15(4), 912\u2013926 (2006)","journal-title":"IEEE\/ASME J. Microelectromech. Syst."},{"key":"9396_CR13","doi-asserted-by":"crossref","unstructured":"Guo, H., Meng, Y.: Dynamic correlation matrix based multi-q learning for a multi-robot system. In: Proceedings of IEEE\/RSJ International Conference on Intelligent Robots and Systems IROS 2008, pp. 840\u2013845 (2008)","DOI":"10.1109\/IROS.2008.4651021"},{"issue":"1","key":"9396_CR14","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1007\/s10846-006-9103-z","volume":"48","author":"D Gu","year":"2007","unstructured":"Gu, D., Yang, E.: Fuzzy policy reinforcement learning in cooperative multi-robot systems. J. Intell. Robot. Syst. 48(1), 7\u201322 (2007)","journal-title":"J. Intell. Robot. Syst."},{"issue":"1","key":"9396_CR15","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/s10846-007-9174-5","volume":"51","author":"DM Kati\u0107","year":"2008","unstructured":"Kati\u0107, D.M., Rodi\u0107, A.D., Vukobratovi\u0107, M.K.: Hybrid dynamic control algorithm for humanoid robots based on reinforcement learning. J. Intell. Robot. Syst. 51(1), 3\u201330 (2008)","journal-title":"J. Intell. Robot. Syst."},{"issue":"2","key":"9396_CR16","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1109\/84.294321","volume":"3","author":"S Konishi","year":"1994","unstructured":"Konishi, S., Fujita, H.: A conveyance system using air flow based on the concept of distributed micro motion systems. IEEE\/ASME J. Microelectromech. Syst. 3(2), 54\u201358 (1994)","journal-title":"IEEE\/ASME J. Microelectromech. Syst."},{"key":"9396_CR17","doi-asserted-by":"crossref","unstructured":"Kuyer, L., Whiteson, S., Bakker, B., Vlassis, N.: Multiagent reinforcement learning for urban traffic control using coordination graphs. In: ECML PKDD \u201908: Proceedings of the 2008 European Conference on Machine Learning and Knowledge Discovery in Databases \u2014 Part I. Lecture Notes in Computer Science, vol. 5211, pp. 656\u2013671. Springer (2008)","DOI":"10.1007\/978-3-540-87479-9_61"},{"key":"9396_CR18","unstructured":"Lauer, M., Riedmiller, M.: An algorithm for distributed reinforcement learning in cooperative multi-agent systems. In: Proc. of the International Conf. on Machine Learning, pp.\u00a0535\u2013542. Morgan Kaufmann (2000). citeseer.ist.psu.edu\/lauer00algorithm.html"},{"key":"9396_CR19","unstructured":"Matignon, L., Laurent, G.J., Le Fort-Piat, N.: A study of fmq heuristic in cooperative multi-agent games. In: Proc. of the Int. Conf. on Autonomous Agents and Multiagent Systems, Workshop 10: Multi-Agent Sequential Decision Making in Uncertain Multi-Agent Domains (2008)"},{"key":"9396_CR20","doi-asserted-by":"crossref","unstructured":"Matignon, L., Laurent, G.J., Le Fort-Piat, N.: Improving reinforcement learning speed for robot control. In: Proc. of the IEEE Int. Conf. on Intelligent Robots and Systems. Beijing, China (2006)","DOI":"10.1109\/IROS.2006.282341"},{"key":"9396_CR21","doi-asserted-by":"crossref","unstructured":"Matignon, L., Laurent, G.J., Le Fort-Piat, N.: Hysteretic q-learning: an algorithm for decentralized reinforcement learning in cooperative multi-agent teams. In: Proc. of the IEEE Int. Conf. on Intelligent Robots and Systems, pp. 64\u201369. San Diego, CA, USA (2007)","DOI":"10.1109\/IROS.2007.4399095"},{"key":"9396_CR22","unstructured":"Matignon, L., Laurent, G.J., Le Fort-Piat, N.: Coordination of independent learners in cooperative markov games. Tech. rep., Institut FEMTO-ST\/UFC-ENSMM-UTBM-CNRS, Universit\u00e9 de Franche-Comt\u00e9, Besan\u00e7on, France (2009). http:\/\/hal.archives-ouvertes.fr\/hal-00370889\/fr\/"},{"key":"9396_CR23","unstructured":"Nakazawa, H., Watamasa, Y., Morita, O.: Electromagnetic micro-parts conveyer with coil-diode modules. In: Proc. of the IEEE International Conference of Solid-State Sensors and Actuators (Transducers \u201999), pp. 1192\u20131195 (1999)"},{"issue":"3","key":"9396_CR24","doi-asserted-by":"crossref","first-page":"387","DOI":"10.1007\/s10458-005-2631-2","volume":"11","author":"L Panait","year":"2005","unstructured":"Panait, L., Luke, S.: Cooperative multi-agent learning: the state of the art. Auton. Agent. Multi-Agent Syst. 11(3), 387\u2013434 (2005)","journal-title":"Auton. Agent. Multi-Agent Syst."},{"key":"9396_CR25","doi-asserted-by":"crossref","unstructured":"Pister, K.S.J., Fearing, R., Howe, R.: A planar air levitated electrostatic actuator system. In: Proc. of the IEEE Workshop on Micro Electro Mechanical Systems (MEMS), pp. 67\u201371. Napa Valley, California (1990)","DOI":"10.1109\/MEMSYS.1990.110250"},{"key":"9396_CR26","unstructured":"Precup, D.: Temporal abstraction in reinforcement learning. Ph.D. thesis, University of Massachusetts, Director-Richard S. Sutton (2000)."},{"issue":"3","key":"9396_CR27","first-page":"333","volume":"10","author":"S Sen","year":"1998","unstructured":"Sen, S., Sekaran, M.: Individual learning of coordination knowledge. JETAI 10(3), 333\u2013356 (1998)","journal-title":"JETAI"},{"issue":"3","key":"9396_CR28","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1023\/A:1007904418265","volume":"21","author":"KT Song","year":"1998","unstructured":"Song, K.T., Sun, W.Y.: Robot control optimization using reinforcement learning. J. Intell. Robot. Syst. 21(3), 221\u2013238 (1998)","journal-title":"J. Intell. Robot. Syst."},{"key":"9396_CR29","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. The MIT Press, Cambridge (1998)"},{"key":"9396_CR30","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1016\/S0004-3702(99)00052-1","volume":"112","author":"RS Sutton","year":"1999","unstructured":"Sutton, R.S., Precup, D., Singh, S.: Between mdps and semi-mdps: learning, planning, and representing knowledge at multiple temporal scales. Artif. Intell. 112, 181\u2013211 (1999)","journal-title":"Artif. Intell."},{"key":"9396_CR31","doi-asserted-by":"crossref","unstructured":"Tan, M.: Multiagent reinforcement learning: independent vs. cooperative agents. In: 10th International Conference on Machine Learning, pp. 330\u2013337 (1993)","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"9396_CR32","doi-asserted-by":"crossref","unstructured":"Wang, Y., de\u00a0Silva, C.W.: Multi-robot box-pushing: single-agent q-learning vs. team q-learning. In: Proc. of IROS, pp. 3694\u20133699 (2006)","DOI":"10.1109\/IROS.2006.281729"},{"issue":"3","key":"9396_CR33","doi-asserted-by":"crossref","first-page":"470","DOI":"10.1016\/j.engappai.2007.05.006","volume":"21","author":"Y Wang","year":"2008","unstructured":"Wang, Y., de\u00a0Silva, C.W.: A machine-learning approach to multi-robot coordination. Eng. Appl. Artif. Intell. 21(3), 470\u2013484 (2008). doi: 10.1016\/j.engappai.2007.05.006","journal-title":"Eng. Appl. Artif. Intell."},{"key":"9396_CR34","volume-title":"Learning from delayed rewards. Ph.D. thesis","author":"CJ Watkins","year":"1989","unstructured":"Watkins, C.J.: Learning from delayed rewards. Ph.D. thesis, Cambridge University, Cambridge, England (1989)"},{"key":"9396_CR35","first-page":"279","volume":"8","author":"C Watkins","year":"1992","unstructured":"Watkins, C., Dayan, P.: Technical note: Q-learning. Mach. Learn. 8, 279\u2013292 (1992)","journal-title":"Mach. Learn."}],"container-title":["Journal of Intelligent & Robotic Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10846-010-9396-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10846-010-9396-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10846-010-9396-9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,17]],"date-time":"2025-02-17T08:35:25Z","timestamp":1739781325000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10846-010-9396-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,2,4]]},"references-count":35,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2010,8]]}},"alternative-id":["9396"],"URL":"https:\/\/doi.org\/10.1007\/s10846-010-9396-9","relation":{},"ISSN":["0921-0296","1573-0409"],"issn-type":[{"value":"0921-0296","type":"print"},{"value":"1573-0409","type":"electronic"}],"subject":[],"published":{"date-parts":[[2010,2,4]]}}}