{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T14:47:48Z","timestamp":1771685268237,"version":"3.50.1"},"publisher-location":"Berlin, Heidelberg","reference-count":15,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783540779476","type":"print"},{"value":"9783540779490","type":"electronic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1007\/978-3-540-77949-0_5","type":"book-chapter","created":{"date-parts":[[2008,2,8]],"date-time":"2008-02-08T04:01:52Z","timestamp":1202443312000},"page":"60-74","source":"Crossref","is-referenced-by-count":12,"title":["Parallel Reinforcement Learning with Linear Function Approximation"],"prefix":"10.1007","author":[{"given":"Matthew","family":"Grounds","sequence":"first","affiliation":[]},{"given":"Daniel","family":"Kudenko","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"5_CR1","doi-asserted-by":"crossref","unstructured":"Tan, M.: Multi-agent reinforcement learning: Independent vs. cooperative agents. In: ICML 1993. Proceedings of the Tenth International Conference on Machine Learning, pp. 330\u2013337 (1993)","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"5_CR2","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44826-8_3","volume-title":"Adaptive Agents and Multi-Agent Systems","author":"L. Nunes","year":"2003","unstructured":"Nunes, L., Oliveira, E.: Cooperative learning using advice exchange. In: Alonso, E., Kudenko, D., Kazakov, D. (eds.) Adaptive Agents and Multi-Agent Systems. LNCS (LNAI), vol.\u00a02636. Springer, Heidelberg (2003)"},{"key":"5_CR3","unstructured":"Whitehead, S.D.: A complexity analysis of cooperative mechanisms in reinforcement learning. In: AAAI 1991. Proceedings of the 9th National Conference on Artificial Intelligence, pp. 607\u2013613 (1991)"},{"key":"5_CR4","unstructured":"Kretchmar, R.M.: Parallel reinforcement learning. In: SCI 2002. Proceedings of the 6th World Conference on Systemics, Cybernetics, and Informatics (2002)"},{"key":"5_CR5","unstructured":"Watkins, C.J.C.H.: Learning from Delayed Rewards. PhD thesis, Cambridge University, U.K. (1989)"},{"key":"5_CR6","unstructured":"Rummery, G.A., Niranjan, M.: On-line Q-learning using connectionist systems. Technical Report TR166, Cambridge University Engineering Dept. (1994)"},{"key":"5_CR7","unstructured":"Sutton, R.S.: Generalization in reinforcement learning: Successful examples using sparse coarse coding. In: Neural Information Processing Systems, vol.\u00a08 (1996)"},{"issue":"3","key":"5_CR8","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1023\/A:1007678930559","volume":"38","author":"S. Singh","year":"2000","unstructured":"Singh, S., Jaakkola, T., Littman, M.L., Szepesvari, C.: Convergence results for single-step on-policy reinforcement learning algorithms. Machine Learning\u00a038(3), 287\u2013308 (2000)","journal-title":"Machine Learning"},{"key":"5_CR9","first-page":"9","volume":"3","author":"R.S. Sutton","year":"1988","unstructured":"Sutton, R.S.: Learning to predict by the methods of temporal differences. Machine Learning\u00a03, 9\u201344 (1988)","journal-title":"Machine Learning"},{"key":"5_CR10","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":"5_CR11","volume-title":"Advances in Parallel Algorithms","author":"T. Archibald","year":"1992","unstructured":"Archibald, T.: Parallel dynamic programming. In: Kronsj\u00f6, L., Shumsheruddin, D. (eds.) Advances in Parallel Algorithms. Blackwell Scientific, Malden (1992)"},{"key":"5_CR12","volume-title":"Parallel Programming with MPI","author":"P.S. Pacheco","year":"1997","unstructured":"Pacheco, P.S.: Parallel Programming with MPI. Morgan Kaufmann, San Francisco (1997)"},{"key":"5_CR13","unstructured":"Grounds, M.J.: Scaling Up Reinforcement Learning using Parallelization and Symbolic Planning. PhD thesis, The University of York, UK (2007)"},{"issue":"1","key":"5_CR14","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1109\/3477.979961","volume":"32","author":"M.N. Ahmadabadi","year":"2002","unstructured":"Ahmadabadi, M.N., Asadpour, M.: Expertness based cooperative Q-learning. IEEE Transactions on Systems, Man and Cybernetics\u00a032(1), 66\u201376 (2002)","journal-title":"IEEE Transactions on Systems, Man and Cybernetics"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Wingate, D., Seppi, K.: P3VI: A partitioned, prioritized, parallel value iterator. In: Proceedings of the 21st International Conference on Machine Learning (2004)","DOI":"10.1145\/1015330.1015440"}],"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_5.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T10:56:50Z","timestamp":1619521010000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-77949-0_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"ISBN":["9783540779476","9783540779490"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-77949-0_5","relation":{},"subject":[]}}