{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T06:53:13Z","timestamp":1761807193698},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"2-4","license":[{"start":{"date-parts":[[2005,9,12]],"date-time":"2005-09-12T00:00:00Z","timestamp":1126483200000},"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":[[2005,12,24]]},"DOI":"10.1007\/s10846-005-5137-x","type":"journal-article","created":{"date-parts":[[2005,9,16]],"date-time":"2005-09-16T13:51:38Z","timestamp":1126878698000},"page":"161-174","source":"Crossref","is-referenced-by-count":28,"title":["A Reinforcement Learning Algorithm in Cooperative Multi-Robot Domains"],"prefix":"10.1007","volume":"43","author":[{"given":"Fernando","family":"Fern??ndez","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Borrajo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lynne E.","family":"Parker","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2005,9,12]]},"reference":[{"key":"15137_CR1","doi-asserted-by":"crossref","DOI":"10.1007\/978-94-017-2053-3","volume-title":"Lazy Learning","author":"D. Aha","year":"1997","unstructured":"Aha, D.: 1997, Lazy Learning, Kluwer Academic Publishers, Dordrecht."},{"key":"15137_CR2","doi-asserted-by":"crossref","unstructured":"Balch, T. and Parker, L. E. (eds): 2002, Robot Teams: from Diversity to Polymorphism. A. K. Peters Publishers.","DOI":"10.1201\/9781439863671"},{"key":"15137_CR3","volume-title":"Dynamic Programming","author":"R. Bellman","year":"1957","unstructured":"Bellman, R.: 1957, Dynamic Programming, Princeton Univ. Press, Princeton, NJ."},{"key":"15137_CR4","volume-title":"Neuro-Dynamic Programming","author":"D. P. Bertsekas","year":"1996","unstructured":"Bertsekas, D. P. and Tsitsiklis, J. N.: 1996, Neuro-Dynamic Programming, Athena Scientific, Bellmon, MA."},{"key":"15137_CR5","volume-title":"Pattern Classification and Scene Analysis","author":"R. O. Duda","year":"1973","unstructured":"Duda, R. O. and Hart, P. E.: 1973, Pattern Classification and Scene Analysis, Wiley, New York."},{"key":"15137_CR6","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"crossref","first-page":"292","DOI":"10.1007\/3-540-45327-X_24","volume-title":"RoboCup-99: Robot Soccer World Cup III","author":"F. Fern\u00e1ndez","year":"2000","unstructured":"Fern\u00e1ndez, F. and Borrajo, D.: 2000, VQQL. Applying vector quantization to reinforcement learning, in: RoboCup-99: Robot Soccer World Cup III, Lecture Notes in Artificial Intelligence, Vol. 1856, Springer, Berlin, pp. 292\u2013303."},{"key":"15137_CR7","unstructured":"Fern\u00e1ndez, F. and Borrajo, D.: 2002, On determinism handling while learning reduced state space representations, in: Proc. of the European Conf. on Artificial Intelligence (ECAI 2002), Lyon, France, July."},{"issue":"3","key":"15137_CR8","first-page":"205","volume":"21","author":"F. Fern\u00e1ndez","year":"2002","unstructured":"Fern\u00e1ndez, F. and Isasi, P.: 2002, Automatic finding of good classifiers following a biologically inspired metaphor, Computing Informatics 21(3), 205\u2013220.","journal-title":"Computing Informatics"},{"issue":"4","key":"15137_CR9","doi-asserted-by":"crossref","first-page":"431","DOI":"10.1023\/B:HEUR.0000034715.70386.5b","volume":"10","author":"F. Fern\u00e1ndez","year":"2004","unstructured":"Fern\u00e1ndez, F. and Isasi, P.: 2004, Evolutionary design of nearest prototype classifiers, J. Heuristics 10(4), 431\u2013454.","journal-title":"J. Heuristics"},{"issue":"4","key":"15137_CR10","first-page":"217","volume":"16","author":"F. Fern\u00e1ndez","year":"2001","unstructured":"Fern\u00e1ndez, F. and Parker, L.: 2001, Learning in large cooperative multi-robot domains, Internat. J. Robotics Automat. 16(4), 217\u2013226.","journal-title":"Internat. J. Robotics Automat."},{"key":"15137_CR11","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"L. P. Kaelbling","year":"1996","unstructured":"Kaelbling, L. P., Littman, M. L., and Moore, A. W.: 1996, Reinforcement learning: A survey, J. Artificial Intelligence Res. 4, 237\u2013285.","journal-title":"J. Artificial Intelligence Res."},{"issue":"2\/3","key":"15137_CR12","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1016\/0004-3702(92)90058-6","volume":"55","author":"S. Mahadevan","year":"1992","unstructured":"Mahadevan, S. and Connell, J.: 1992, Automatic programming of behaviour-based robots using reinforcement learning, Artificial Intelligence 55(2\/3), 311\u2013365.","journal-title":"Artificial Intelligence"},{"issue":"3","key":"15137_CR13","first-page":"199","volume":"21","author":"A. W. Moore","year":"1995","unstructured":"Moore, A. W. and Atkeson, C. G.: 1995, The parti-game algorithm for variable resolution reinforcement learning in multidimensional state-spaces, Machine Learning 21(3), 199\u2013233.","journal-title":"Machine Learning"},{"key":"15137_CR14","unstructured":"Ng, A. Y. and Russel, S.: 2000, Algorithms for inverse reinforcement learning, in: Proc. of the Seventeenth Internat. Conf. on Machine Learning."},{"key":"15137_CR15","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1007\/978-4-431-67919-6_37","volume-title":"Distributed Autonomous Robotic Systems, Vol. 4","author":"L. Parker","year":"2000","unstructured":"Parker, L. and Touzet, C.: 2000, Multi-robot learning in a cooperative observation task, in: L. E. Parker, G. Bekey and J. Barhen (eds), Distributed Autonomous Robotic Systems, Vol. 4, Springer, Berlin, pp. 391\u2013401."},{"issue":"3","key":"15137_CR16","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1023\/A:1015256330750","volume":"12","author":"L. E. Parker","year":"2002","unstructured":"Parker, L. E.: 2002, Distributed algorithms for multi-robot observation of multiple moving targets, Autonom. Robots 12(3), 231\u2013255.","journal-title":"Autonom. Robots"},{"key":"15137_CR17","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","volume-title":"Markov Decision Processes \u2013 Discrete Stochastic Dynamic Programming","author":"M. L. Puterman","year":"1994","unstructured":"Puterman, M. L.: 1994, Markov Decision Processes \u2013 Discrete Stochastic Dynamic Programming, Wiley, New York."},{"issue":"2","key":"15137_CR18","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1177\/105971239700600201","volume":"6","author":"J. C. Santamar\u00eda","year":"1998","unstructured":"Santamar\u00eda, J. C., Sutton, R. S., and Ram, A.: 1998, Experiments with reinforcement learning in problems with continuous state and action spaces, Adaptive Behavior 6(2), 163\u2013218.","journal-title":"Adaptive Behavior"},{"key":"15137_CR19","unstructured":"Smart, W. D.: 2002, Making reinforcement learning work on real robots, PhD Thesis, Department of Computer Science at Brown University, Providence, RI."},{"key":"15137_CR20","unstructured":"Stone, P. and Veloso, M.: 2000, Multiagent systems: A survey from a machine learning perspective, Autonom. Robots 8(3)."},{"key":"15137_CR21","first-page":"257","volume":"8","author":"G. Tesauro","year":"1992","unstructured":"Tesauro, G.: 1992, Practical issues in temporal difference learning, Machine Learning 8, 257\u2013277.","journal-title":"Machine Learning"},{"key":"15137_CR22","first-page":"59","volume":"22","author":"J. N. Tsitsiklis","year":"1996","unstructured":"Tsitsiklis, J. N. and Van Roy, B.: 1996, Feature-based methods for large scale dynamic programming, Machine Learning 22, 59\u201394.","journal-title":"Machine Learning"},{"key":"15137_CR23","unstructured":"Watkins C. J. C. H.: 1989, Learning from delayed rewards, PhD Thesis, King\u2019s College, Cambridge, UK."}],"container-title":["Journal of Intelligent and Robotic Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10846-005-5137-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10846-005-5137-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10846-005-5137-x","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,4]],"date-time":"2023-05-04T15:36:37Z","timestamp":1683214597000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10846-005-5137-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2005,9,12]]},"references-count":23,"journal-issue":{"issue":"2-4","published-print":{"date-parts":[[2005,12,24]]}},"alternative-id":["5137"],"URL":"https:\/\/doi.org\/10.1007\/s10846-005-5137-x","relation":{},"ISSN":["0921-0296","1573-0409"],"issn-type":[{"value":"0921-0296","type":"print"},{"value":"1573-0409","type":"electronic"}],"subject":[],"published":{"date-parts":[[2005,9,12]]}}}