{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T22:32:25Z","timestamp":1725489145843},"publisher-location":"Berlin, Heidelberg","reference-count":22,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540001317"},{"type":"electronic","value":"9783540361312"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2002]]},"DOI":"10.1007\/3-540-36131-6_23","type":"book-chapter","created":{"date-parts":[[2007,8,12]],"date-time":"2007-08-12T05:42:30Z","timestamp":1186897350000},"page":"224-232","source":"Crossref","is-referenced-by-count":3,"title":["An Analysis of the Pheromone Q-Learning Algorithm"],"prefix":"10.1007","author":[{"given":"Ndedi","family":"Monekosso","sequence":"first","affiliation":[]},{"given":"Paolo","family":"Remagnino","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2002,11,5]]},"reference":[{"key":"23_CR1","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1007\/BF02224053","volume":"37","author":"R. Beckers","year":"1990","unstructured":"R. Beckers, J. L. Deneubourg, S. Goss, and J. M. Pasteels. Collective decision making through food recruitment. Ins. Soc., 37:258\u2013267, 1990.","journal-title":"Ins. Soc."},{"key":"23_CR2","doi-asserted-by":"publisher","first-page":"397","DOI":"10.1016\/S0022-5193(05)80686-1","volume":"159","author":"R. Beckers","year":"1992","unstructured":"R. Beckers, J.L. Deneubourg, and S. Goss. Trails and u-turns in the selection of the shortest path by the ant lasius niger. Journal of Theoretical Biology, 159:397\u20134151, 1992.","journal-title":"Journal of Theoretical Biology"},{"key":"23_CR3","unstructured":"D.P. Bertsekas and J.N. Tsitsiklis. Neuro-Dynamic Programming. Athena Scientific, 1996."},{"key":"23_CR4","doi-asserted-by":"crossref","unstructured":"E. Bonabeau, M. Dorigo, and G. Theraulaz. Swarm intelligence, From Natural to Artificial Systems. Oxford University Press, 1999.","DOI":"10.1093\/oso\/9780195131581.001.0001"},{"key":"23_CR5","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1007\/BF00694700","volume":"88","author":"M. C. Cammaerts-Tricot","year":"1974","unstructured":"M. C. Cammaerts-Tricot. Piste et pheromone attraction chez la fourmi myrmica ruba. Journal of Computational Physiology, 88:373\u2013382, 1974.","journal-title":"Journal of Computational Physiology"},{"key":"23_CR6","unstructured":"G. Di Caro and M. Dorigo. Antnet: a mobile agents approach to adaptive routing. Technical Report: IRIDIA\/97-12, Universite Libre de Bruxelles, Belgium. http:\/\/citeseer.nj.nec.com\/dicaro97antnet.html ."},{"key":"23_CR7","first-page":"39","volume":"34","author":"A. Colorni","year":"1993","unstructured":"A. Colorni, M. Dorigo, and V. Maniezzo. Ant system for job-shop scheduling. Belgian Journal of OR, statistics and computer science, 34:39\u201353, 1993.","journal-title":"Belgian Journal of OR, statistics and computer science"},{"key":"23_CR8","unstructured":"A. Colorni, M. Dorigo, and G. Theraulaz. Distributed optimzation by ant colonies. In Proceedings First European Conf. on Artificial Life, pages 134\u2013142, 1991."},{"key":"23_CR9","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1080\/08927014.1989.9525500","volume":"1","author":"J.L. Deneubourg","year":"1993","unstructured":"J.L. Deneubourg and S. Goss. Collective patterns and decision making. Ethol. Ecol. and Evol., 1:295\u2013311, 1993.","journal-title":"Ethol. Ecol. and Evol."},{"key":"23_CR10","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1109\/4235.585892","volume":"1","author":"M. Dorigo","year":"1997","unstructured":"M. Dorigo and L. M. Gambardella. Ant colony system: A cooperative learning approach to the travelling salesman problem. IEEE Trans. on Evol. Comp., 1:53\u201366, 1997.","journal-title":"IEEE Trans. on Evol. Comp."},{"key":"23_CR11","first-page":"1","volume":"26","author":"M. Dorigo","year":"1996","unstructured":"M. Dorigo, V. Maniezzo, and A. Colorni. The ant system: Optimization by a colony of cooperatin agents. IEEE Trans. on Systems, Man, and Cybernetics, 26:1\u201313, 1996.","journal-title":"IEEE Trans. on Systems, Man, and Cybernetics"},{"key":"23_CR12","doi-asserted-by":"crossref","unstructured":"L. M. Gambardella and M. Dorigo. Ant-q:A reinforcement learning approach to the traveling salesman problem. In Proc. 12Th ICML, pages 252\u2013260, 1995.","DOI":"10.1016\/B978-1-55860-377-6.50039-6"},{"key":"23_CR13","unstructured":"L. M. Gambardella, E. D. Taillard, and M. Dorigo. Ant colonies for the qap. Journal of Operational Research society, 1998."},{"key":"23_CR14","doi-asserted-by":"crossref","unstructured":"S. Goss, S. Aron, J.L. Deneubourg, and J. M. Pasteels. Self-organized shorcuts in the argentine ants. Naturwissenschaften, pages 579\u2013581, 1989.","DOI":"10.1007\/BF00462870"},{"key":"23_CR15","unstructured":"L. R. Leerink, S. R. Schultz, and M. A. Jabri. A reinforcement learning exploration strategy based on ant foraging mechanisms. In Proc. 6Th Australian Conference on Neural Nets, 1995."},{"key":"23_CR16","unstructured":"N. Monekosso and P. Remagnino. Phe-q:Apheromone based q-learning. In AI2001:Advances in Artificial Intelligence, 14Th Australian Joint Conf. on A.I., pages 345\u2013355, 2001."},{"key":"23_CR17","doi-asserted-by":"crossref","unstructured":"H. Van Dyke Parunak and S. Brueckner. Ant-like missionnaries and cannibals: Synthetic pheromones for distributed motion control. In Proc. of ICMAS\u201900, 2000.","DOI":"10.1145\/336595.337572"},{"key":"23_CR18","unstructured":"H. Van Dyke Parunak, S. Brueckner, J. Sauter, and J. Posdamer. Mechanisms and military applications for synthetic pheromones. In Proc. 5Th International Conference Autonomous Agents, Montreal, Canada, 2001."},{"key":"23_CR19","unstructured":"R. S. Sutton and A.G. Barto. Reinforcement Learning. MIT Press, 1998."},{"key":"23_CR20","doi-asserted-by":"publisher","first-page":"1185","DOI":"10.1162\/neco.1994.6.6.1185","volume":"6","author":"T. Jaakkola","year":"1994","unstructured":"T. Jaakkola, M.I. Jordan, and S.P. Singh. On the convergence of stochastic iterative dynamic programming algorithms. Neural Computation, 6:1185\u20131201, 1994.","journal-title":"Neural Computation"},{"key":"23_CR21","doi-asserted-by":"crossref","unstructured":"R. T. Vaughan, K. Stoy, G. S. Sukhatme, and M. J. Mataric. Whistling in the dark: Cooperative trail following in uncertain localization space. In Proc. 4Th International Conference on Autonomous Agents, Barcelona, Spain, 2000.","DOI":"10.1145\/336595.337351"},{"key":"23_CR22","unstructured":"C. J. C. H. Watkins. Learning with delayed rewards. PhD thesis, University of Cambridge, 1989."}],"container-title":["Lecture Notes in Computer Science","Advances in Artificial Intelligence \u2014 IBERAMIA 2002"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/3-540-36131-6_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,21]],"date-time":"2021-08-21T16:26:28Z","timestamp":1629563188000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/3-540-36131-6_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2002]]},"ISBN":["9783540001317","9783540361312"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/3-540-36131-6_23","relation":{},"ISSN":["0302-9743"],"issn-type":[{"type":"print","value":"0302-9743"}],"subject":[],"published":{"date-parts":[[2002]]}}}