{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T08:32:09Z","timestamp":1758875529751},"publisher-location":"Berlin, Heidelberg","reference-count":11,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540232377"},{"type":"electronic","value":"9783540286455"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2004]]},"DOI":"10.1007\/978-3-540-28645-5_25","type":"book-chapter","created":{"date-parts":[[2010,9,20]],"date-time":"2010-09-20T22:13:58Z","timestamp":1285020838000},"page":"245-254","source":"Crossref","is-referenced-by-count":22,"title":["Heuristically Accelerated Q\u2013Learning: A New Approach to Speed Up Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Reinaldo A. C.","family":"Bianchi","sequence":"first","affiliation":[]},{"given":"Carlos H. C.","family":"Ribeiro","sequence":"additional","affiliation":[]},{"given":"Anna H. R.","family":"Costa","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"25_CR1","volume-title":"Dynamic Programming: Deterministic and Stochastic Models","author":"D.P. Bertsekas","year":"1987","unstructured":"Bertsekas, D.P.: Dynamic Programming: Deterministic and Stochastic Models. Prentice-Hall, Upper Saddle River (1987)"},{"key":"25_CR2","doi-asserted-by":"crossref","first-page":"6791","DOI":"10.1038\/35017500","volume":"406","author":"E. Bonabeau","year":"2000","unstructured":"Bonabeau, E., Dorigo, M., Theraulaz, G.: Inspiration for optimization from social insect behaviour. Nature 406 [6791] (2000)","journal-title":"Nature"},{"key":"25_CR3","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1613\/jair.904","volume":"16","author":"C. Drummond","year":"2002","unstructured":"Drummond, C.: Accelerating reinforcement learning by composing solutions of automatically identified subtasks. Journal of Artificial Intelligence Research\u00a016, 59\u2013104 (2002)","journal-title":"Journal of Artificial Intelligence Research"},{"issue":"2\/3","key":"25_CR4","doi-asserted-by":"publisher","first-page":"325","DOI":"10.1023\/A:1017944732463","volume":"49","author":"D. Foster","year":"2002","unstructured":"Foster, D., Dayan, P.: Structure in the space of value functions. Machine Learning\u00a049(2\/3), 325\u2013346 (2002)","journal-title":"Machine Learning"},{"key":"25_CR5","doi-asserted-by":"crossref","unstructured":"Gambardella, L., Dorigo, M.: Ant\u2013Q: A reinforcement learning approach to the traveling salesman problem. In: Proceedings of the ML 1995 \u2013 Twelfth International Conference on Machine Learning, pp. 252\u2013260 (1995)","DOI":"10.1016\/B978-1-55860-377-6.50039-6"},{"issue":"2","key":"25_CR6","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1109\/TSSC.1968.300136","volume":"4","author":"P.E. Hart","year":"1968","unstructured":"Hart, P.E., Nilsson, N.J., Raphael, B.: A formal basis for the heuristic determination of minimum cost paths. IEEE Transactions on Systems Science and Cybernetics\u00a04(2), 100\u2013107 (1968)","journal-title":"IEEE Transactions on Systems Science and Cybernetics"},{"key":"25_CR7","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"L.P. Kaelbling","year":"1996","unstructured":"Kaelbling, L.P., Littman, M.L., Moore, A.W.: Reinforcement learning: A survey. Journal of Artificial Intelligence Research\u00a04, 237\u2013285 (1996)","journal-title":"Journal of Artificial Intelligence Research"},{"key":"25_CR8","unstructured":"Littman, M.L., Szepesv\u00e1ri, C.: A generalized reinforcement learning model: Convergence and applications. In: Procs. of the Thirteenth International Conf. on Machine Learning (ICML 1996), pp. 310\u2013318 (1996)"},{"key":"25_CR9","volume-title":"Machine Learning","author":"T. Mitchell","year":"1997","unstructured":"Mitchell, T.: Machine Learning. McGraw Hill, New York (1997)"},{"key":"25_CR10","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4471-3392-6","volume-title":"Mobile Robotics: A Practical Introduction","author":"U. Nehmzow","year":"2000","unstructured":"Nehmzow, U.: Mobile Robotics: A Practical Introduction. Springer, Berlin (2000)"},{"key":"25_CR11","unstructured":"Watkins, C.J.C.H.: Learning from Delayed Rewards. PhD thesis, University of Cambridge (1989)"}],"container-title":["Lecture Notes in Computer Science","Advances in Artificial Intelligence \u2013 SBIA 2004"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-28645-5_25.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,3]],"date-time":"2021-05-03T03:30:22Z","timestamp":1620012622000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-28645-5_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2004]]},"ISBN":["9783540232377","9783540286455"],"references-count":11,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-28645-5_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2004]]}}}