{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T09:46:02Z","timestamp":1743155162699,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":21,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642299452"},{"type":"electronic","value":"9783642299469"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-29946-9_24","type":"book-chapter","created":{"date-parts":[[2012,5,18]],"date-time":"2012-05-18T17:01:49Z","timestamp":1337360509000},"page":"237-248","source":"Crossref","is-referenced-by-count":6,"title":["Multi-Task Reinforcement Learning: Shaping and Feature Selection"],"prefix":"10.1007","author":[{"given":"Matthijs","family":"Snel","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shimon","family":"Whiteson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"24_CR1","unstructured":"Asmuth, J., Littman, M.L., Zinkov, R.: Potential-based shaping in model-based reinforcement learning. In: Proceedings of the 23rd AAAI Conference on Artificial Intelligence, pp. 604\u2013609. The AAAI Press (2008)"},{"issue":"1","key":"24_CR2","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L. Breiman","year":"2001","unstructured":"Breiman, L.: Random forests. Machine Learning\u00a045(1), 5\u201332 (2001)","journal-title":"Machine Learning"},{"issue":"6","key":"24_CR3","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1177\/1059712308092835","volume":"16","author":"S. Elfwing","year":"2008","unstructured":"Elfwing, S., Uchibe, E., Doya, K., Christensen, H.I.: Co-evolution of shaping: Rewards and meta-parameters in reinforcement learning. Adaptive Behavior\u00a016(6), 400\u2013412 (2008)","journal-title":"Adaptive Behavior"},{"key":"24_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"474","DOI":"10.1007\/978-3-642-15880-3_36","volume-title":"Machine Learning and Knowledge Discovery in Databases","author":"H. Hachiya","year":"2010","unstructured":"Hachiya, H., Sugiyama, M.: Feature Selection for Reinforcement Learning: Evaluating Implicit State-Reward Dependency via Conditional Mutual Information. In: Balc\u00e1zar, J.L., Bonchi, F., Gionis, A., Sebag, M. (eds.) ECML PKDD 2010. LNCS, vol.\u00a06321, pp. 474\u2013489. Springer, Heidelberg (2010)"},{"key":"24_CR5","unstructured":"Jong, N.K., Stone, P.: State abstraction discovery from irrelevant state variables. In: IJCAI 2005 (2005)"},{"key":"24_CR6","doi-asserted-by":"crossref","unstructured":"Konidaris, G.D., Barto, A.G.: Autonomous shaping: Knowledge transfer in reinforcement learning. In: Proc. 23rd International Conference on Machine Learning, pp. 489\u2013496 (2006)","DOI":"10.1145\/1143844.1143906"},{"key":"24_CR7","unstructured":"Lazaric, A., Ghavamzadeh, M.: Bayesian multi-task reinforcement learning. In: ICML, pp. 599\u2013606 (2010)"},{"key":"24_CR8","unstructured":"Li, L., Walsh, T.J., Littman, M.L.: Towards a unified theory of state abstraction for MDPs. In: Aritificial Intelligence and Mathematics (2006)"},{"key":"24_CR9","doi-asserted-by":"crossref","unstructured":"Mahadevan, S.: Representation discovery in sequential decision making. In: AAAI (2010)","DOI":"10.1609\/aaai.v24i1.7766"},{"key":"24_CR10","unstructured":"Ng, A.Y., Harada, D., Russell, S.: Policy invariance under reward transformations: Theory and application to reward shaping. In: Proc. 16th International Conference on Machine Learning (1999)"},{"key":"24_CR11","doi-asserted-by":"crossref","unstructured":"Parr, R., Li, L., Taylor, G., Painter-Wakefield, C., Littman, M.L.: An analysis of linear models, linear value-function approximation, and feature selection for reinforcement learning. In: ICML, pp. 752\u2013759 (2008)","DOI":"10.1145\/1390156.1390251"},{"key":"24_CR12","unstructured":"Petrik, M., Taylor, G., Parr, R., Zilberstein, S.: Feature selection using regularization in approximate linear programs for Markov decision processes. In: ICML, pp. 871\u2013878 (2010)"},{"key":"24_CR13","unstructured":"Singh, S., Lewis, R.L., Barto, A.G.: Where do rewards come from? In: Proc. 31st Annual Conference of the Cognitive Science Society, pp. 2601\u20132606 (2009)"},{"key":"24_CR14","doi-asserted-by":"crossref","unstructured":"Snel, M., Whiteson, S.: Multi-task evolutionary shaping without pre-specified representations. In: Genetic and Evolutionary Computation Conference, GECCO 2010 (2010)","DOI":"10.1145\/1830483.1830671"},{"key":"24_CR15","unstructured":"Sorg, J., Singh, S.: Transfer via soft homomorphisms. In: Proc. 8th Int. Conf. on Autonomous Agents and Multiagent Systems (AAMAS 2009), pp. 741\u2013748 (2009)"},{"key":"24_CR16","doi-asserted-by":"crossref","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. The MIT Press (1998)","DOI":"10.1109\/TNN.1998.712192"},{"key":"24_CR17","doi-asserted-by":"crossref","unstructured":"Tanaka, F., Yamamura, M.: Multitask reinforcement learning on the distribution of MDPs. In: Proc. 2003 IEEE International Symposium on Computational Intelligence in Robotics and Automation (CIRA 2003), pp. 1108\u20131113 (2003)","DOI":"10.1109\/CIRA.2003.1222152"},{"issue":"1","key":"24_CR18","first-page":"1633","volume":"10","author":"M.E. Taylor","year":"2009","unstructured":"Taylor, M.E., Stone, P.: Transfer learning for reinforcement learning domains: A survey. Journal of Machine Learning Research\u00a010(1), 1633\u20131685 (2009)","journal-title":"Journal of Machine Learning Research"},{"key":"24_CR19","unstructured":"Walsh, T.J., Li, L., Littman, M.L.: Transferring state abstractions between MDPs. In: ICML 2006 Workshop on Structural Knowledge Transfer for Machine Learning (2006)"},{"key":"24_CR20","unstructured":"Wiewiora, E., Cottrell, G., Elkan, C.: Principled methods for advising reinforcement learning agents. In: Proc. 20th International Conference on Machine Learning, pp. 792\u2013799 (2003)"},{"key":"24_CR21","doi-asserted-by":"crossref","unstructured":"Wilson, A., Fern, A., Ray, S., Tadepalli, P.: Multi-task reinforcement learning: a hierarchical Bayesian approach. In: ICML, pp. 1015\u20131022 (2007)","DOI":"10.1145\/1273496.1273624"}],"container-title":["Lecture Notes in Computer Science","Recent Advances in Reinforcement Learning"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-29946-9_24.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T09:07:53Z","timestamp":1743152873000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-29946-9_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642299452","9783642299469"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-29946-9_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2012]]}}}