{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T02:07:05Z","timestamp":1725502025408},"publisher-location":"Berlin, Heidelberg","reference-count":27,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540779476"},{"type":"electronic","value":"9783540779490"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1007\/978-3-540-77949-0_13","type":"book-chapter","created":{"date-parts":[[2008,2,8]],"date-time":"2008-02-08T04:01:52Z","timestamp":1202443312000},"page":"169-187","source":"Crossref","is-referenced-by-count":1,"title":["Solving Multi-stage Games with Hierarchical Learning Automata That Bootstrap"],"prefix":"10.1007","author":[{"given":"Maarten","family":"Peeters","sequence":"first","affiliation":[]},{"given":"Katja","family":"Verbeeck","sequence":"additional","affiliation":[]},{"given":"Ann","family":"Now\u00e9","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"13_CR1","unstructured":"Tuyls, K.: Learning in Multi-Agent Systems: An Evolutionary Game Theoretic Approach. PhD thesis, Vrije Universiteit Brussel (2004)"},{"key":"13_CR2","unstructured":"Claus, C., Boutilier, C.: The dynamics of reinforcement learning in cooperative multiagent systems. In: AAAI 1998. Proceedings of the Fifteenth National Conference of Artificial Intelligence, Madison, WI, pp. 746\u2013752 (1998)"},{"key":"13_CR3","doi-asserted-by":"crossref","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., Peeters, M., Tuyls, K.: Multi-agent reinforcement learning in stochastic single and multi-stage games. In: Kudenko, D., Kazakov, D., Alonso, E. (eds.) Adaptive Agents and Multi-Agent Systems II, pp. 275\u2013294. Springer, Heidelberg (2005)"},{"key":"13_CR4","doi-asserted-by":"crossref","unstructured":"Verbeeck, K.: Coordinated Exploration in Multi-Agent Reinforcement Learning. PhD thesis, Vrije Universiteit Brussel (2004)","DOI":"10.1145\/1082473.1082645"},{"key":"13_CR5","first-page":"275","volume-title":"Adaptive Agents and Multi-Agent Systems II","author":"S. Kapetanakis","year":"2005","unstructured":"Kapetanakis, S., Kudenko, D., Strens, M.J.A.: Learning to coordinate using commitment sequences in cooperative multi-agent systems. In: Kudenko, D., Kazakov, D., Alonso, E. (eds.) Adaptive Agents and Multi-Agent Systems II, pp. 275\u2013294. Springer, Heidelberg (2005)"},{"issue":"10","key":"13_CR6","first-page":"1345","volume":"22","author":"M.L. Tsetlin","year":"1961","unstructured":"Tsetlin, M.L.: On the behavior of finite automata in random media. Avtomatika i Telemekhanika\u00a022(10), 1345\u20131354 (1961)","journal-title":"Avtomatika i Telemekhanika"},{"issue":"4","key":"13_CR7","first-page":"323","volume":"SMC-4","author":"K.S. Narendra","year":"1974","unstructured":"Narendra, K.S., Thathachar, M.A.L.: Learning automata - a survey. IEEE_J_SMC\u00a0SMC-4(4), 323\u2013334 (1974)","journal-title":"IEEE_J_SMC"},{"key":"13_CR8","volume-title":"Learning Automata: An Introduction","author":"K.S. Narendra","year":"1989","unstructured":"Narendra, K.S., Thathachar, M.A.L.: Learning Automata: An Introduction. Prentice-Hall, Englewood Cliffs (1989)"},{"key":"13_CR9","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4419-9052-5","volume-title":"Networks of Learning Automata: Techniques for Online Stochastic Optimization","author":"M.A.L. Thathachar","year":"2004","unstructured":"Thathachar, M.A.L., Sastry, P.S.: Networks of Learning Automata: Techniques for Online Stochastic Optimization. Kluwer Academic Publishers, Dordrecht (2004)"},{"key":"13_CR10","doi-asserted-by":"crossref","unstructured":"Now\u00e9, A., Verbeeck, K., Peeters, M.: Learning automata as a basis for multi-agent reinforcement learning. In: Tuyls, K., t Hoen, P.J., Verbeeck, K., Sen, S. (eds.) LAMAS 2005. LNCS (LNAI), vol.\u00a03898, pp. 71\u201385. Springer, Heidelberg (2006)","DOI":"10.1007\/11691839_3"},{"key":"13_CR11","volume-title":"Reinforcement Learning: An Introduction","author":"R.S. Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge, MA (1998)"},{"key":"13_CR12","unstructured":"Verbeeck, K., Now\u00e9, A., Parent, J., Tuyls, K.: Exploring selfish reinforcement learning in repeated games with stochastic rewards. Journal of Autonomous Agents and Multi-agent Systems (to appear)"},{"issue":"11","key":"13_CR13","first-page":"383","volume":"3","author":"L. Panait","year":"2005","unstructured":"Panait, L., Luke, S.: Cooperative multi-agent learning: The state of the art. Autonomous Agents and Multi-Agent Systems\u00a03(11), 383\u2013434 (2005)","journal-title":"Autonomous Agents and Multi-Agent Systems"},{"key":"13_CR14","unstructured":"Boutilier, C.: Sequential optimality and coordination in multiagent systems. In: Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence, pp. 478\u2013485 (1996)"},{"issue":"3","key":"13_CR15","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1109\/TSMC.1981.4308659","volume":"SMC-11","author":"M.A.L. Thathachar","year":"1981","unstructured":"Thathachar, M.A.L., Ramakrishnan, K.R.: A hierarchical system of learning automata. IEEE Transactions on Systems, Man, and Cybernetics\u00a0SMC-11(3), 236\u2013241 (1981)","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics"},{"key":"13_CR16","unstructured":"Ramakrishnan, K.R.: Hierarchical systems and cooperative games of learning automata. PhD thesis, Indian Institute of Science, Bangalore, India (1982)"},{"key":"13_CR17","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"crossref","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.) Adaptive Agents and Multi-Agent Systems II. LNCS (LNAI), vol.\u00a03394, pp. 275\u2013294. Springer, Heidelberg (2005)"},{"issue":"3","key":"13_CR18","first-page":"279","volume":"8","author":"C. Watkins","year":"1992","unstructured":"Watkins, C., Dayan, P.: Q-learning. Machine Learning\u00a08(3), 279\u2013292 (1992)","journal-title":"Machine Learning"},{"key":"13_CR19","unstructured":"Shoham, Y., Powers, R., Grenager, T.: Multi-agent reinforcement learning: a critical survey. Technical report, Stanford University (2003)"},{"key":"13_CR20","volume-title":"Reinforcement Learning An Introduction","author":"R.S. Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning An Introduction. MIT Press, Cambridge (1998)"},{"key":"13_CR21","doi-asserted-by":"crossref","unstructured":"Peeters, M., Verbeeck, K., Now\u00e9, A.: The effect of bootstrapping in multi-automata reinforcement learning. In: IEEE Symposium Series on Computational Intelligence, International Symposium on Approximate Dynamic Programming and Reinforcement Learning (2007)","DOI":"10.1109\/ADPRL.2007.368172"},{"key":"13_CR22","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., Moore, A.P.: Reinforcement learning: A survey. Journal of Artificial Intelligence Research\u00a04, 237\u2013285 (1996)","journal-title":"Journal of Artificial Intelligence Research"},{"key":"13_CR23","first-page":"185","volume":"16","author":"J. Tsitsiklis","year":"1994","unstructured":"Tsitsiklis, J.: Asynchronous stochastic approximation and q-learning. Machine Learning\u00a016, 185\u2013202 (1994)","journal-title":"Machine Learning"},{"issue":"2","key":"13_CR24","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1109\/21.101158","volume":"21","author":"K.S. Narendra","year":"1991","unstructured":"Narendra, K.S., Parthasarathy, K.: Learning automata approach to hierarchical multiobjective analysis. IEEE Transactions on Systems, Man, and Cybernetics\u00a021(2), 263\u2013273 (1991)","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics"},{"key":"13_CR25","unstructured":"Peeters, M., Now\u00e9, A., Verbeeck, K.: Bootstrapping versus monte carlo in a learning automata hierarchy. Adaptive Learning Agents and Multi-Agent Systems, 61\u201371 (2006)"},{"key":"13_CR26","unstructured":"Peeters, M., Now\u00e9, A., Verbeeck, K.: Toward bootstrapping in a hierarchy of learning automata. In: Proceedings of the Seventh European Workshop on Reinforcement Learning, pp. 31\u201332 (2005)"},{"key":"13_CR27","unstructured":"Van\u00a0de Wege, L.: Learning automata as a framework for multi-agent reinforcement learning: Convergence issues in tree-structured multi-stage games. Master\u2019s thesis, Vrije Universiteit Brussel (2006)"}],"container-title":["Lecture Notes in Computer Science","Adaptive Agents and Multi-Agent Systems III. Adaptation and Multi-Agent Learning"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-77949-0_13.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,16]],"date-time":"2023-05-16T11:56:48Z","timestamp":1684238208000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-77949-0_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"ISBN":["9783540779476","9783540779490"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-77949-0_13","relation":{},"subject":[]}}