{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,4,5]],"date-time":"2022-04-05T10:03:44Z","timestamp":1649153024208},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"1-2","license":[{"start":{"date-parts":[[2013,11,19]],"date-time":"2013-11-19T00:00:00Z","timestamp":1384819200000},"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":[[2014,4]]},"DOI":"10.1007\/s10846-013-9980-x","type":"journal-article","created":{"date-parts":[[2013,11,17]],"date-time":"2013-11-17T23:56:54Z","timestamp":1384732614000},"page":"529-544","source":"Crossref","is-referenced-by-count":8,"title":["Distributed Learning for Planning Under Uncertainty Problems with Heterogeneous Teams"],"prefix":"10.1007","volume":"74","author":[{"given":"N. Kemal","family":"Ure","sequence":"first","affiliation":[]},{"given":"Girish","family":"Chowdhary","sequence":"additional","affiliation":[]},{"given":"Yu Fan","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Jonathan P.","family":"How","sequence":"additional","affiliation":[]},{"given":"John","family":"Vian","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2013,11,19]]},"reference":[{"key":"9980_CR1","unstructured":"Bertsekas, D.: Dynamic Programming and Optimal Control. Athena Scientific (2005)"},{"key":"9980_CR2","doi-asserted-by":"crossref","unstructured":"Bethke, B., Bertuccelli, L.F., How, J.P.: Experimental demonstration of adaptive MDP-based planning with model uncertainty. In: AIAA Guidance Navigation and Control. Honolulu, Hawaii (2008)","DOI":"10.2514\/6.2008-6322"},{"issue":"2","key":"9980_CR3","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. EEE Trans. Syst. Man Cyber. Part C Appl. Rev. I 38(2), 156\u2013172 (2008)","journal-title":"EEE Trans. Syst. Man Cyber. Part C Appl. Rev. I"},{"key":"9980_CR4","doi-asserted-by":"crossref","unstructured":"Busoniu, L., Babuska, R., Schutter, B.D., Ernst, D.: Reinforcement Learning and Dynamic Programming Using Function Approximators. CRC Press (2010)","DOI":"10.1201\/9781439821091"},{"issue":"4","key":"9980_CR5","doi-asserted-by":"crossref","first-page":"912","DOI":"10.1109\/TRO.2009.2022423","volume":"25","author":"HL Choi","year":"2009","unstructured":"Choi, H.L,, Brunet, L., How, J.P.: Consensus-based decentralized auctions for robust task allocation. IEEE Trans. Robot. 25(4), 912\u2013926 (2009). doi: 10.1109\/TRO.2009.2022423","journal-title":"IEEE Trans. Robot."},{"issue":"2","key":"9980_CR6","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1109\/MSP.2011.943495","volume":"29","author":"P Djuric","year":"2012","unstructured":"Djuric, P., Wang, Y.: Distributed bayesian learning in multiagent systems: improving our understanding of its capabilities and limitations. IEEE Signal Process. Mag. 29(2), 65\u201376 (2012). doi: 10.1109\/MSP.2011.943495","journal-title":"IEEE Signal Process. Mag."},{"key":"9980_CR7","unstructured":"Geramifard, A., Doshi, F., Redding, J., Roy, N., How, J.: Online discovery of feature dependencies. In: Getoor, L., Scheffer, T. (eds.) International Conference on Machine Learning (ICML), pp. 881\u2013888. ACM (2011)"},{"issue":"2","key":"9980_CR8","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1109\/MCS.2007.914691","volume":"28","author":"JP How","year":"2008","unstructured":"How, J.P., Bethke, B., Frank, A., Dale, D., Vian, J.: Real-time indoor autonomous vehicle test environment. IEEE Control Syst. Mag. 28(2), 51\u201364 (2008)","journal-title":"IEEE Control Syst. Mag."},{"key":"9980_CR9","doi-asserted-by":"crossref","unstructured":"Krishnamurthy, V.: Quickest time detection and constrained optimal social learning with variance penalty. In: 49th IEEE Conference on Decision and Control (CDC), pp. 1102\u20131107. IEEE (2010)","DOI":"10.1109\/CDC.2010.5717548"},{"key":"9980_CR10","unstructured":"Kushner, H.J., Yin, G.G.: Convergence of indirect adaptive asynchronous value iteration algorithms. Springer (2003)"},{"key":"9980_CR11","doi-asserted-by":"crossref","unstructured":"LaValle, S.: Planning Algorithms. Cambridge University Press (2006)","DOI":"10.1017\/CBO9780511546877"},{"issue":"1","key":"9980_CR12","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1023\/A:1008807102993","volume":"4","author":"DC MacKenzie","year":"1997","unstructured":"MacKenzie, D.C., Arkin, R., Cameron, J.M.: Multiagent mission specification and execution. Auton. Robot. 4(1), 29\u201352 (1997)","journal-title":"Auton. Robot."},{"issue":"2","key":"9980_CR13","doi-asserted-by":"crossref","first-page":"697","DOI":"10.1016\/j.cirp.2006.10.004","volume":"55","author":"L Monostori","year":"2006","unstructured":"Monostori, L., V\u00e1ncza, J., Kumara, S.R.: Agent-based systems for manufacturing. CIRP Annals-Manufacturing Technology 55(2), 697\u2013720 (2006)","journal-title":"CIRP Annals-Manufacturing Technology"},{"key":"9980_CR14","unstructured":"Painter-Wakefield, C., Parr, R.: Greedy algorithms for sparse reinforcement learning. In: International Conference on Machine Learning (ICML), pp. 968\u2013975. ACM (2012)"},{"issue":"10","key":"9980_CR15","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","volume":"22","author":"SJ Pan","year":"2010","unstructured":"Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345\u20131359 (2010)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"3","key":"9980_CR16","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. Agents Multi-Agent Syst. 11(3), 387\u2013434 (2005)","journal-title":"Auton. Agents Multi-Agent Syst."},{"key":"9980_CR17","doi-asserted-by":"crossref","unstructured":"Powell, W.: Approximate Dynamic Programming: Solving the Curses of Dimensionality, pp. 225\u2013262. Wiley-Interscience (2007)","DOI":"10.1002\/9780470182963.ch7"},{"key":"9980_CR18","unstructured":"Puterman, M.L.: Markov Decision Processes: Discrete Stochastic Dynamic Programming, vol. 414. Wiley (2009)"},{"key":"9980_CR19","unstructured":"Redding, J.D.: Approximate multi-agent planning in dynamic and uncertain environments. PhD thesis, Massachusetts Institute of Technology, Department of Aeronautics and Astronautics, Cambridge MA (2012)"},{"key":"9980_CR20","doi-asserted-by":"crossref","unstructured":"Redding, J.D., Toksoz, T., Ure, N.K., Geramifard, A., How, J.P., Vavrina, M., Vian, J.: Persistent distributed multi-agent missions with automated battery management. In: AIAA Guidance, Navigation, and Control Conference (GNC), (AIAA-2011-6480) (2011)","DOI":"10.2514\/6.2011-6480"},{"key":"9980_CR21","unstructured":"Russell, S., Norvig, P.: Artificial Intelligence: A Modern Approach, 2nd edn. Prentice-Hall, Englewood Cliffs, NJ (2003)"},{"key":"9980_CR22","volume-title":"Reinforcement Learning, an Introduction","author":"R Sutton","year":"1998","unstructured":"Sutton, R., Barto, A.: Reinforcement Learning, an Introduction. MIT Press, Cambridge, MA (1998)"},{"key":"9980_CR23","unstructured":"Sutton, R., Szepesv\u00e1ri, C., Geramifard, A., Bowling, M.: Dyna-style planning with linear function approximation and prioritized sweeping. In: Proceedings of the 25th International Conference on Machine Learning. Helsinki, Finland (2008)"},{"key":"9980_CR24","unstructured":"Thrun, S., Burgard, W., Fox, D.: Probabilistic Robotics (Intelligent Robotics and Autonomous Agents). The MIT Press (2005)"},{"key":"9980_CR25","unstructured":"Toksoz, T.: Design and implementation of an automated battery management platform. Master\u2019s thesis, Massachusetts Institute of Technology (2012)"},{"key":"9980_CR26","doi-asserted-by":"crossref","unstructured":"Ure, N.K., Chowdhary, G., Redding, J., Toksoz, T., How, J., Vavrina, M., Vian, J.: Experimental demonstration of efficient multi-agent learning and planning for persistent missions in uncertain environments. In: Conference on Guidance Navigation and Control. AIAA, Minneapolis, MN (2012)","DOI":"10.2514\/6.2012-4622"},{"key":"9980_CR27","doi-asserted-by":"crossref","unstructured":"Ure, N.K., Geramifard, A., Chowdhary, G., How, J.P.: Adaptive planning for Markov decision processes with uncertain transition models via incremental feature dependency discovery. In: European Conference on Machine Learning (ECML). http:\/\/acl.mit.edu\/papers\/Ure12ECML.pdf (2012)","DOI":"10.1007\/978-3-642-33486-3_7"},{"key":"9980_CR28","doi-asserted-by":"crossref","unstructured":"Ure, N.K., Chowdhary, G., Chen, Y.F., How, J.P., Vian. J.: Decentralized learning based planning multiagent missions in presence of actuator failures. In: International Conference on Unmanned Aircraft Systems. IEEE, Atlanta GA (2013)","DOI":"10.1109\/ICUAS.2013.6564803"},{"key":"9980_CR29","unstructured":"Ure, N.K., Chowdhary, G., Chen, Y.F., How, J.P., Vian, J.: Health-aware decentralized planning and learning for large-scale multiagent missions. In: Conference on Guidance Navigation and Control. AIAA, Washington DC (2013)"},{"key":"9980_CR30","doi-asserted-by":"crossref","unstructured":"Ure, N.K., Chowdhary, G., How, J.P., Vavarina, M., Vian, J.: Health aware planning under uncertainty for uav missions with heterogeneous teams. In: Proceedings of the European Control Conference. Zurich, Switzerland (2013) (to appear)","DOI":"10.23919\/ECC.2013.6669789"},{"key":"9980_CR31","unstructured":"Weibull, J.W.: Evolutionary Game Theory. MIT Press (1997)"},{"key":"9980_CR32","unstructured":"Yao, H., Sutton, R.S., Bhatnagar, S., Dongcui, D., Szepesv\u00e1ri, C.: Multi-step dynamic planning for policy evaluation and control. In: NIPS, pp. 2187\u20132195 (2009)"}],"container-title":["Journal of Intelligent & Robotic Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10846-013-9980-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10846-013-9980-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10846-013-9980-x","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,2]],"date-time":"2019-08-02T01:24:03Z","timestamp":1564709043000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10846-013-9980-x"}},"subtitle":["Scaling Up the Multiagent Planning with Distributed Learning and Approximate Representations"],"short-title":[],"issued":{"date-parts":[[2013,11,19]]},"references-count":32,"journal-issue":{"issue":"1-2","published-print":{"date-parts":[[2014,4]]}},"alternative-id":["9980"],"URL":"https:\/\/doi.org\/10.1007\/s10846-013-9980-x","relation":{},"ISSN":["0921-0296","1573-0409"],"issn-type":[{"value":"0921-0296","type":"print"},{"value":"1573-0409","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,11,19]]}}}