{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T12:23:43Z","timestamp":1783427023902,"version":"3.54.6"},"publisher-location":"Berlin, Heidelberg","reference-count":14,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783540857754","type":"print"},{"value":"9783540857761","type":"electronic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1007\/978-3-540-85776-1_13","type":"book-chapter","created":{"date-parts":[[2008,8,23]],"date-time":"2008-08-23T08:01:12Z","timestamp":1219478472000},"page":"144-156","source":"Crossref","is-referenced-by-count":2,"title":["Robustness Analysis of SARSA(\u03bb): Different Models of Reward and Initialisation"],"prefix":"10.1007","author":[{"given":"Marek","family":"Grze\u015b","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Kudenko","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"13_CR1","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","volume-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","author":"M.L. Puterman","year":"1994","unstructured":"Puterman, M.L.: Markov Decision Processes: Discrete Stochastic Dynamic Programming. John Wiley & Sons, Inc., New York (1994)"},{"key":"13_CR2","unstructured":"Sutton, R.S.: Temporal credit assignment in reinforcement learning. PhD thesis, Department of Computer Science, University of Massachusetts, Amherst (1984)"},{"key":"13_CR3","unstructured":"Loch, J., Singh, S.: Using eligibility traces to find the best memoryless policy in partially observable Markov Decision Processes. In: Proceedings of the 15th International Conferrence on Machine Learning, pp. 323\u2013331 (1998)"},{"key":"13_CR4","first-page":"9","volume":"3","author":"R. Sutton","year":"1988","unstructured":"Sutton, R.: Learning to predict by the methods of temporal differences. Machine Learning\u00a03, 9\u201344 (1988)","journal-title":"Machine Learning"},{"key":"13_CR5","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)"},{"issue":"1\u20133","key":"13_CR6","first-page":"123","volume":"22","author":"S.P. Singh","year":"1996","unstructured":"Singh, S.P., Sutton, R.S.: Reinforcement learning with replacing eligibility traces. Machine Learning\u00a022(1\u20133), 123\u2013158 (1996)","journal-title":"Machine Learning"},{"key":"13_CR7","first-page":"283","volume":"22","author":"J. Peng","year":"1996","unstructured":"Peng, J., Williams, R.J.: Incremental multi-step Q-learning. Machine Learning\u00a022, 283\u2013290 (1996)","journal-title":"Machine Learning"},{"key":"13_CR8","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1613\/jair.135","volume":"2","author":"P. Cichosz","year":"1995","unstructured":"Cichosz, P.: Truncating temporal differences: On the efficient implementation of TD(\u03bb) for reinforcement learning. Journal of Artificial Intelligence Research\u00a02, 287\u2013318 (1995)","journal-title":"Journal of Artificial Intelligence Research"},{"key":"13_CR9","first-page":"257","volume":"8","author":"G. Tesauro","year":"1992","unstructured":"Tesauro, G.: Practical issues in temporal difference learning. Machine Learning\u00a08, 257\u2013277 (1992)","journal-title":"Machine Learning"},{"key":"13_CR10","doi-asserted-by":"crossref","unstructured":"Sutton, R.S.: Integrated architectures for learning, planning, and reacting based on approximating dynamic programming. In: Proceedings of the 7th International Conference on Machine Learning, pp. 216\u2013224 (1990)","DOI":"10.1016\/B978-1-55860-141-3.50030-4"},{"key":"13_CR11","volume-title":"Artificial Intelligence: A Modern Approach","author":"S.J. Russell","year":"2002","unstructured":"Russell, S.J., Norvig, P.: Artificial Intelligence: A Modern Approach, 2nd edn. Prentice-Hall, Englewood Cliffs (2002)","edition":"2"},{"key":"13_CR12","doi-asserted-by":"crossref","unstructured":"Jong, N.K., Stone, P.: Model-based exploration in continuous state spaces. In: The 7th Symposium on Abstraction, Reformulation, and Approximation (2007)","DOI":"10.1007\/978-3-540-73580-9_21"},{"key":"13_CR13","first-page":"1017","volume":"8","author":"R.H. Crites","year":"1996","unstructured":"Crites, R.H., Barto, A.G.: Improving elevator performance using reinforcement learning. Advances in Neural Information Processing Systems\u00a08, 1017\u20131023 (1996)","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"3","key":"13_CR14","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"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence: Methodology, Systems, and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-85776-1_13.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T07:49:12Z","timestamp":1619509752000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-85776-1_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"ISBN":["9783540857754","9783540857761"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-85776-1_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[]}}