{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T14:59:21Z","timestamp":1777129161569,"version":"3.51.4"},"publisher-location":"Berlin, Heidelberg","reference-count":13,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783540730064","type":"print"},{"value":"9783540730071","type":"electronic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1007\/978-3-540-73007-1_14","type":"book-chapter","created":{"date-parts":[[2007,9,20]],"date-time":"2007-09-20T17:34:35Z","timestamp":1190309675000},"page":"110-118","source":"Crossref","is-referenced-by-count":10,"title":["Heuristic Search Based Exploration in Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Ngo","family":"Anh Vien","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nguyen","family":"Hoang Viet","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"SeungGwan","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"TaeChoong","family":"Chung","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"14_CR1","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":"14_CR2","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":"14_CR3","unstructured":"Wiering, M.A.: Explorations in efficient reinforcement learning. Ph.D. dissertation, University of Amsterdam IDSIA (February 1999)"},{"key":"14_CR4","first-page":"531","volume-title":"Advances in Neural Information Processing Systems 4","author":"S. Thrun","year":"1992","unstructured":"Thrun, S., Moller, K.: Active exploration in dynamic environments. In: Moody, J.E., Hanson, S.J., Lippmann, R. (eds.) Advances in Neural Information Processing Systems 4, pp. 531\u2013538. Morgan Kaufmann, Washington (1992)"},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"Nguyen, D., Widrow, B.: The truck backer upper: An example of self-learning in neural networks. In: Proceedings of the First International Joint Conference on Neural Networks Washington DC San Diego, Washington, DC, IEEE TAB Neural Network Committee (1989)","DOI":"10.1109\/IJCNN.1989.118723"},{"key":"14_CR6","volume-title":"Advances in Neural Information Processing Systems","author":"S.B. Thrun","year":"1991","unstructured":"Thrun, S.B., Moller, K., Linden, A.: Planning with an adaptive world model. In: Advances in Neural Information Processing Systems, Morgan Kaufmann, San Mateo (1991)"},{"key":"14_CR7","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/1090.001.0001","volume-title":"Adaptation in Natural and Artificial System","author":"J.H. Holland","year":"1992","unstructured":"Holland, J.H.: Adaptation in Natural and Artificial System, 2nd edn. MIT Press, Cambridge (1992)","edition":"2"},{"issue":"1","key":"14_CR8","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1109\/4235.728210","volume":"2","author":"W. Macready","year":"1998","unstructured":"Macready, W., Wolpert, D.H.: Bandit problems and the Exploration\/Exploitation Tradeoff. IEEE Transactions on Evolutionary Computation\u00a02(1), 2\u201322 (1998)","journal-title":"IEEE Transactions on Evolutionary Computation"},{"key":"14_CR9","volume-title":"Modern Heuristic Techniques for Combinatorial Problems","author":"C.R. Reeves","year":"1993","unstructured":"Reeves, C.R.: Modern Heuristic Techniques for Combinatorial Problems. Blackwell Scientific Publication, Oxford (1993)"},{"key":"14_CR10","volume-title":"Modern Heuristic Techniques for Combinatorial Problems","author":"K. Downsland","year":"1993","unstructured":"Downsland, K.: Simulated annealing. In: Downsland, K. (ed.) Modern Heuristic Techniques for Combinatorial Problems, Blackwell Scientific Publication, Oxford (1993)"},{"key":"14_CR11","unstructured":"Davies, S., Ng, A., Moore, A.: Applying Online Search Techniques to Continuous-State Reinforcement Learning. In: Proceedings of the Fifteenth National Conference on Artificial Intelligence, AAAI (1998)"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Atiya, A.F., Parlos, A.G., Ingber, L.: A reinforcement learning method based on adaptive simulated annealing. In: Proceedings of the 46th IEEE International Midwest Symposium on Circuits and Systems, MWSCAS \u201903, vol.1, December 2003, pp. 121\u2013124 (2003)","DOI":"10.1109\/MWSCAS.2003.1562233"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Abramsan, M., Wechsler, H.: Competitive reinforcement learning for combinatorial problems. In: International Joint Conference on Neural Network (2001)","DOI":"10.1109\/IJCNN.2001.938727"}],"container-title":["Lecture Notes in Computer Science","Computational and Ambient Intelligence"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-73007-1_14.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T09:54:30Z","timestamp":1619517270000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-73007-1_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"ISBN":["9783540730064","9783540730071"],"references-count":13,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-73007-1_14","relation":{},"subject":[]}}