{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T17:58:51Z","timestamp":1725472731573},"publisher-location":"Berlin, Heidelberg","reference-count":11,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540497875"},{"type":"electronic","value":"9783540497882"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2006]]},"DOI":"10.1007\/11941439_18","type":"book-chapter","created":{"date-parts":[[2006,11,17]],"date-time":"2006-11-17T09:53:05Z","timestamp":1163757185000},"page":"141-150","source":"Crossref","is-referenced-by-count":0,"title":["Enhanced Temporal Difference Learning Using Compiled Eligibility Traces"],"prefix":"10.1007","author":[{"given":"Peter","family":"Vamplew","sequence":"first","affiliation":[]},{"given":"Robert","family":"Ollington","sequence":"additional","affiliation":[]},{"given":"Mark","family":"Hepburn","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"18_CR1","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":"18_CR2","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, 123\u2013158 (1996)","journal-title":"Machine Learning"},{"key":"18_CR3","volume-title":"On-line Q-Learning Using Connectionist Systems","author":"G. Rummery","year":"1994","unstructured":"Rummery, G., Niranjan, M.: On-line Q-Learning Using Connectionist Systems. Cambridge University Engineering Department, Cambridge (1994)"},{"key":"18_CR4","unstructured":"Watkins, C.J.C.H.: Learning from Delayed Rewards, PhD Thesis, Cambridge University (1989)"},{"key":"18_CR5","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1145\/122344.122377","volume":"2","author":"R.S. Sutton","year":"1991","unstructured":"Sutton, R.S.: Dyna, an integrated architecture for learning, planning and reacting. SIGART Bulletin\u00a02, 160\u2013163 (1991)","journal-title":"SIGART Bulletin"},{"key":"18_CR6","unstructured":"Kaelbling, L.P.: Learning to Achieve Goals. In: Proceedings of the Thirteenth International Joint Conference on Artificial Intelligence, Chamb\u00e9ry, France (1993)"},{"key":"18_CR7","unstructured":"Ollington, R., Vamplew, P.: Concurrent Q-Learning for Autonomous Mapping and Navigation. In: The 2nd International Conference on Computational Intelligence, Robotics and Autonomous Systems, Singapore (2003)"},{"key":"18_CR8","doi-asserted-by":"publisher","first-page":"1185","DOI":"10.1162\/neco.1994.6.6.1185","volume":"6","author":"T. Jaakkola","year":"1994","unstructured":"Jaakkola, T., Jordan, M.I., Singh, S.P.: On the convergence of stochastic iterative dynamic programming algorithms. Neural Computation\u00a06, 1185\u20131201 (1994)","journal-title":"Neural Computation"},{"key":"18_CR9","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":"18_CR10","first-page":"1038","volume-title":"Advances in Neural Information Processing Systems: Proceedings of the 1995 Conference","author":"R.S. Sutton","year":"1996","unstructured":"Sutton, R.S.: Generalisation in reinforcement learning: Successful examples using sparse coarse coding. In: Touretzky, D.S., Mozer, M.C., Hasselmo, M.E. (eds.) Advances in Neural Information Processing Systems: Proceedings of the 1995 Conference, pp. 1038\u20131044. The MIT Press, Cambridge (1996)"},{"key":"18_CR11","unstructured":"Kretchmar, R.M., Anderson, C.W.: Comparison of CMACs and RBFs for local function approximators in reinforcement learning. In: IEEE International Conference on Neural Networks (1997)"}],"container-title":["Lecture Notes in Computer Science","AI 2006: Advances in Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/11941439_18.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T07:51:05Z","timestamp":1619509865000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/11941439_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006]]},"ISBN":["9783540497875","9783540497882"],"references-count":11,"URL":"https:\/\/doi.org\/10.1007\/11941439_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2006]]}}}