{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T06:41:10Z","timestamp":1725518470924},"publisher-location":"Berlin, Heidelberg","reference-count":10,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540875352"},{"type":"electronic","value":"9783540875369"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1007\/978-3-540-87536-9_41","type":"book-chapter","created":{"date-parts":[[2008,9,5]],"date-time":"2008-09-05T15:23:30Z","timestamp":1220628210000},"page":"397-406","source":"Crossref","is-referenced-by-count":0,"title":["A Continuous Internal-State Controller for Partially Observable Markov Decision Processes"],"prefix":"10.1007","author":[{"given":"Yuki","family":"Taniguchi","sequence":"first","affiliation":[]},{"given":"Takeshi","family":"Mori","sequence":"additional","affiliation":[]},{"given":"Shin","family":"Ishii","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"41_CR1","unstructured":"Aberdeen, D., Baxter, J.: Scaling Internal State Policy-Gradient Methods for POMDPs. In: Proceedings of the 19th International Conference on Machine Learning, pp. 3\u201310 (2002)"},{"key":"41_CR2","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1613\/jair.678","volume":"13","author":"M. Hauskrecht","year":"2000","unstructured":"Hauskrecht, M.: Value-function approximations for partially observable Markov decision processes. Journal of Artificial Intelligence Research\u00a013, 33\u201399 (2000)","journal-title":"Journal of Artificial Intelligence Research"},{"key":"41_CR3","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/S0004-3702(98)00023-X","volume":"101","author":"L.P. Kaelbling","year":"1998","unstructured":"Kaelbling, L.P., Littman, M.L., Cassandra, A.R.: Planning and acting in partially observable stochastic domains. Artificial Intelligence\u00a0101, 99\u2013134 (1998)","journal-title":"Artificial Intelligence"},{"key":"41_CR4","doi-asserted-by":"crossref","unstructured":"Littman, M.L.: Markov games as a framework for multi-agent reinforcement learning. In: Proceedings of the 11th International Conference on Machine Learning, pp. 157\u2013163 (1994)","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"41_CR5","unstructured":"Stone, P., Veloso, M.: Multiagent Systems: A Survey from a Machine Learning Perspective. Autonomous Robotics\u00a08(3) (2000)"},{"key":"41_CR6","volume-title":"An introduction to reinforcement learning","author":"R. Sutton","year":"1998","unstructured":"Sutton, R., Barto, A.: An introduction to reinforcement learning. MIT Press, Cambridge (1998)"},{"key":"41_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1007\/978-3-540-74690-4_24","volume-title":"Artificial Neural Networks \u2013 ICANN 2007","author":"Y. Taniguchi","year":"2007","unstructured":"Taniguchi, Y., Mori, T., Ishii, S.: Reinforcement Learning for Cooperative Actions in a Partially Observable Multi-Agent System. In: de S\u00e1, J.M., Alexandre, L.A., Duch, W., Mandic, D.P. (eds.) ICANN 2007. LNCS, vol.\u00a04668, pp. 229\u2013238. Springer, Heidelberg (2007)"},{"key":"41_CR8","unstructured":"Thrun, S.: Monte Carlo POMDPs: Advances in Neural Information Processing Systems, vol.\u00a012, pp. 1064\u20131070 (2000)"},{"key":"41_CR9","first-page":"229","volume":"8","author":"R.J. Williams","year":"1992","unstructured":"Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine Learning\u00a08, 229\u2013256 (1992)","journal-title":"Machine Learning"},{"key":"41_CR10","unstructured":"Whitehead, S.D.: A complexity analysis of cooperative mechanisms in reinforcement leaning. In: Proc. of the 9th National Conf. on Artificial Intelligence, vol.\u00a02, pp. 607\u2013613 (1991)"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks - ICANN 2008"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-87536-9_41.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T12:00:59Z","timestamp":1619524859000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-87536-9_41"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"ISBN":["9783540875352","9783540875369"],"references-count":10,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-87536-9_41","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[]}}