{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T20:35:48Z","timestamp":1742934948880,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":19,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642237829"},{"type":"electronic","value":"9783642237836"}],"license":[{"start":{"date-parts":[[2011,1,1]],"date-time":"2011-01-01T00:00:00Z","timestamp":1293840000000},"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":[[2011]]},"DOI":"10.1007\/978-3-642-23783-6_21","type":"book-chapter","created":{"date-parts":[[2011,8,17]],"date-time":"2011-08-17T18:41:51Z","timestamp":1313606511000},"page":"326-340","source":"Crossref","is-referenced-by-count":1,"title":["Reinforcement Learning through Global Stochastic Search in N-MDPs"],"prefix":"10.1007","author":[{"given":"Matteo","family":"Leonetti","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luca","family":"Iocchi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Subramanian","family":"Ramamoorthy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"21_CR1","unstructured":"Auer, P., Jaksch, T., Ortner, R.: Near-optimal regret bounds for reinforcement learning. In: Koller, D., Schuurmans, D., Bengio, Y., Bottou, L. (eds.) Advances in Neural Information Processing Systems, vol.\u00a021, pp. 89\u201396 (2009)"},{"issue":"4","key":"21_CR2","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1613\/jair.806","volume":"15","author":"J. Baxter","year":"2001","unstructured":"Baxter, J., Bartlett, P.L.: Infinite-horizon policy-gradient estimation. Journal of Artificial Intelligence Research\u00a015(4), 319\u2013350 (2001)","journal-title":"Journal of Artificial Intelligence Research"},{"key":"21_CR3","unstructured":"Crook, P.A.: Learning in a state of confusion: Employing active perception and reinforcement learning in partially observable worlds. Technical report, University of Edinburgh (2006)"},{"key":"21_CR4","unstructured":"Jung, T., Polani, D.: Learning robocup-keepaway with kernels. In: JMLR: Workshop and Conference Proceedings (Gaussian Processes in Practice), vol.\u00a01, pp. 33\u201357 (2007)"},{"key":"21_CR5","unstructured":"Kalyanakrishnan, S., Stone, P.: An empirical analysis of value function-based and policy search reinforcement learning. In: Proceedings of The 8th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2009, SC 2009. International Foundation for Autonomous Agents and Multiagent Systems, Richland, pp. 749\u2013756 (2009)"},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"Kalyanakrishnan, S., Stone, P.: Learning Complementary Multiagent Behaviors: A Case Study. In: Proceedings of the 13th RoboCup International Symposium, pp. 153\u2013165 (2009)","DOI":"10.1007\/978-3-642-11876-0_14"},{"key":"21_CR7","unstructured":"Leonetti, M., Iocchi, L.: Improving the performance of complex agent plans through reinforcement learning. In: Proceedings of the 9th International Conference on Autonomous Agents and Multiagent Systems, vol.\u00a01, pp. 723\u2013730 (2010)"},{"key":"21_CR8","doi-asserted-by":"crossref","unstructured":"Littman, M.L.: Memoryless policies: Theoretical limitations and practical results. In: From Animals to Animats 3: Proceedings of the Third International Conference on Simulation of Adaptive Behavior, pp. 238\u2013247 (1994)","DOI":"10.7551\/mitpress\/3117.003.0041"},{"key":"21_CR9","unstructured":"Loch, J., Singh, S.: Using eligibility traces to find the best memoryless policy in partially observable Markov decision processes. In: Proceedings of the Fifteenth International Conference on Machine Learning, pp. 323\u2013331 (1998)"},{"key":"21_CR10","unstructured":"Pendrith, M.D., McGarity, M.: An analysis of direct reinforcement learning in non-markovian domains. In: Proceedings of the Fifteenth International Conference on Machine Learning (ICML), pp. 421\u2013429 (1998)"},{"key":"21_CR11","unstructured":"Perkins, T.J.: Reinforcement learning for POMDPs based on action values and stochastic optimization. In: Proceedings of the National Conference on Artificial Intelligence, pp. 199\u2013204 (2002)"},{"key":"21_CR12","unstructured":"Perkins, T.J., Pendrith, M.D.: On the existence of fixed points for Q-learning and Sarsa in partially observable domains. In: Proceedings of the Nineteenth International Conference on Machine Learning, pp. 490\u2013497 (2002)"},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Singh, S.P., Sutton, R.S.: Reinforcement learning with replacing eligibility traces. In: Recent Advances in Reinforcement Learning, pp. 123\u2013158 (1996)","DOI":"10.1007\/978-0-585-33656-5_7"},{"key":"21_CR14","doi-asserted-by":"publisher","DOI":"10.1002\/0471722138","volume-title":"Introduction to Stochastic Search and Optimization","author":"J.C. Spall","year":"2003","unstructured":"Spall, J.C.: Introduction to Stochastic Search and Optimization, 1st edn. John Wiley & Sons, Inc., New York (2003)","edition":"1"},{"issue":"3","key":"21_CR15","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1177\/105971230501300301","volume":"13","author":"P. Stone","year":"2005","unstructured":"Stone, P., Sutton, R.S., Kuhlmann, G.: Reinforcement learning for RoboCup-soccer keepaway. Adaptive Behavior\u00a013(3), 165\u2013188 (2005)","journal-title":"Adaptive Behavior"},{"key":"21_CR16","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":"21_CR17","first-page":"1","volume-title":"Proceedings of the 6th International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS 2007","author":"M.E. Taylor","year":"2007","unstructured":"Taylor, M.E., Whiteson, S., Stone, P.: Transfer via inter-task mappings in policy search reinforcement learning. In: Proceedings of the 6th International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS 2007, pp. 1\u201337. ACM, New York (2007)"},{"key":"21_CR18","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1007\/s10994-005-0460-9","volume":"59","author":"S. Whiteson","year":"2005","unstructured":"Whiteson, S., Kohl, N., Miikkulainen, R., Stone, P.: Evolving soccer keepaway players through task decomposition. Machine Learning\u00a059, 5\u201330 (2005), doi:10.1007\/s10994-005-0460-9","journal-title":"Machine Learning"},{"key":"21_CR19","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780199269181.001.0001","volume-title":"Strategic learning and its limits","author":"H. Young","year":"2004","unstructured":"Young, H.: Strategic learning and its limits. Oxford University Press, USA (2004)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-23783-6_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,10]],"date-time":"2024-04-10T07:31:45Z","timestamp":1712734305000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-23783-6_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011]]},"ISBN":["9783642237829","9783642237836"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-23783-6_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2011]]}}}