{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T06:05:23Z","timestamp":1771481123552,"version":"3.50.1"},"publisher-location":"Berlin, Heidelberg","reference-count":20,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783540330530","type":"print"},{"value":"9783540330592","type":"electronic"}],"license":[{"start":{"date-parts":[[2006,1,1]],"date-time":"2006-01-01T00:00:00Z","timestamp":1136073600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2006]]},"DOI":"10.1007\/11691839_3","type":"book-chapter","created":{"date-parts":[[2006,3,6]],"date-time":"2006-03-06T07:31:37Z","timestamp":1141630297000},"page":"71-85","source":"Crossref","is-referenced-by-count":26,"title":["Learning Automata as a Basis for Multi Agent Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Ann","family":"Now\u00e9","sequence":"first","affiliation":[]},{"given":"Katja","family":"Verbeeck","sequence":"additional","affiliation":[]},{"given":"Maarten","family":"Peeters","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"3_CR1","series-title":"Santa Fe Institute studies in the sciences of complexity","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780195131581.001.0001","volume-title":"Swarm Intelligence, From Natural to Artificial Systems","author":"E. Bonabeau","year":"1999","unstructured":"Bonabeau, E., Dorigo, M., Theraulaz, G.: Swarm Intelligence, From Natural to Artificial Systems. Santa Fe Institute studies in the sciences of complexity. Oxford University Press, Oxford (1999)"},{"key":"3_CR2","unstructured":"Boutilier, C.: Planning, learning and coordination in multiagent decision processes. In: Proceedings of the 6th Conference on Theoretical Aspects of Rationality and Knowledge, Renesse, Holland, pp. 195\u2013210 (1996)"},{"key":"3_CR3","unstructured":"Boutilier, C.: Sequential optimality and coordination in multiagent systems. In: Proceedings of the 16th International Joint Conference on Artificial Intelligence, Stockholm, Sweden, pp. 478\u2013485 (1999)"},{"key":"3_CR4","volume-title":"Stochastic Models for Learning","author":"R.R. Bush","year":"1958","unstructured":"Bush, R.R., Mosteller, F.: Stochastic Models for Learning. Wiley, New York (1958)"},{"key":"3_CR5","unstructured":"Claus, C., Boutilier, C.: The dynamics of reinforcement learning in cooperative multiagent systems. In: Proceedings of the 15th National Conference on Artificial Intelligence, pp. 746\u2013752 (1998)"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Colorni, A., Dorigo, M., Maffioli, F., Maniezzo, V., Righini, G., Trubian, M.: Heuristics from nature for hard combinatorial optimization problems. International Transactions in Operational Research (1996)","DOI":"10.1111\/j.1475-3995.1996.tb00032.x"},{"key":"3_CR7","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1162\/106454699568728","volume":"5","author":"M. Dorigo","year":"1999","unstructured":"Dorigo, M., Caro, G.D., Gambardella, L.M.: Ant algorithms for discrete optimization. Artificial Life\u00a05, 137\u2013172 (1999)","journal-title":"Artificial Life"},{"key":"3_CR8","volume-title":"New Ideas In Optimization","author":"M. Dorigo","year":"1999","unstructured":"Dorigo, M., Caro, G.D.: The ant colony optimization meta-heuristic. In: Corne, D., Dorigo, M., Glover, F. (eds.) New Ideas In Optimization. McGraw-Hill, Maidenhaid (1999)"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Dorigo, M., Maniezzo, V., Colorni, A.: The ant system: Optimization by a colony of cooperating agents. IEE Transactions on Systems, Man, and Cybernetics (1996)","DOI":"10.1109\/3477.484436"},{"key":"3_CR10","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/1290.001.0001","volume-title":"Ant Colony Optimization","author":"M. Dorigo","year":"2004","unstructured":"Dorigo, M., St\u00fctzle, T.: Ant Colony Optimization. MIT Press, Cambridge (2004)"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Littman, M.: Markov games as a framework for multi-agent reinforcement learning. In: Proceedings of the 11th International Conference on Machine Learning, pp. 322\u2013328 (1994)","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"3_CR12","volume-title":"Learning Automata: An Introduction","author":"K. Narendra","year":"1989","unstructured":"Narendra, K., Thathachar, M.: Learning Automata: An Introduction. Prentice- Hall International, Inc., Upper Saddle River (1989)"},{"key":"3_CR13","unstructured":"Narendra, K.S., Parthasarathy, K.: Learning automata approach to hierarchical multiobjective analysis. Technical Report Report No. 8811, Electrical Engineering Yale University, New Haven, Connecticut (1988)"},{"key":"3_CR14","doi-asserted-by":"publisher","first-page":"608","DOI":"10.1109\/12.862220","volume":"49","author":"B.J. Oommen","year":"2000","unstructured":"Oommen, B.J., Roberts, T.D.: Continuous learning automata solutions to the capacity assignment problem. IEEE Transactions on Computations\u00a049, 608\u2013620 (2000)","journal-title":"IEEE Transactions on Computations"},{"key":"3_CR15","volume-title":"Reinforcement Learning: An Introduction","author":"R. Sutton","year":"1998","unstructured":"Sutton, R., Barto, A.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)"},{"key":"3_CR16","unstructured":"Tsetlin, M.L.: Automaton theory and modelling of biological systems. Mathematics in Science and Engineering, vol.\u00a0102 (1973)"},{"key":"3_CR17","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1109\/3468.736368","volume":"29","author":"C. Unsal","year":"1999","unstructured":"Unsal, C., Kachroo, P., Bay, J.S.: Multiple stochastic learning automata for vehicule path control in an automated highway system. IEEE Transactions on Systems, Man, and Cybernetics, Part A\u00a029, 120\u2013128 (1999)","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics, Part A"},{"key":"3_CR18","unstructured":"Verbeeck, K.: Coordinated Exploration in Multi-Agent Reinforcement Learning. PhD thesis, Computational Modeling Lab, Vrije Universiteit Brussel, Belgium (2004)"},{"key":"3_CR19","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1007\/978-3-540-32274-0_18","volume-title":"Adaptive Agents and Multi-Agent Systems II","author":"K. Verbeeck","year":"2005","unstructured":"Verbeeck, K., Now\u00e9, A., Tuyls, K., Peeters, M.: Multi-agent reinforcement learning in stochastic single and multi-stage games. In: Kudenko, D., Kazakov, D., Alonso, E. (eds.) AAMAS 2004. LNCS (LNAI), vol.\u00a03394, pp. 275\u2013294. Springer, Heidelberg (2005)"},{"key":"3_CR20","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1109\/TAC.1986.1104342","volume":"31","author":"R.M. Wheeler","year":"1986","unstructured":"Wheeler, R.M., Narendra, K.S.: Decentralized learning in finite markov chains. IEEE Transactions on Automatic Control\u00a0AC-31, 519\u2013526 (1986)","journal-title":"IEEE Transactions on Automatic Control"}],"container-title":["Lecture Notes in Computer Science","Learning and Adaption in Multi-Agent Systems"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/11691839_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,7,24]],"date-time":"2021-07-24T11:27:36Z","timestamp":1627126056000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/11691839_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006]]},"ISBN":["9783540330530","9783540330592"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/11691839_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2006]]}}}