{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T07:43:54Z","timestamp":1725522234715},"publisher-location":"Berlin, Heidelberg","reference-count":26,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540926948"},{"type":"electronic","value":"9783540926955"}],"license":[{"start":{"date-parts":[[2008,1,1]],"date-time":"2008-01-01T00:00:00Z","timestamp":1199145600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2008]]},"DOI":"10.1007\/978-3-540-92695-5_15","type":"book-chapter","created":{"date-parts":[[2008,12,16]],"date-time":"2008-12-16T10:11:59Z","timestamp":1229422319000},"page":"192-205","source":"Crossref","is-referenced-by-count":2,"title":["Tuning Local Search by Average-Reward Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Steven","family":"Prestwich","sequence":"first","affiliation":[]}],"member":"297","reference":[{"key":"15_CR1","unstructured":"Boese, K.D.: Cost Versus Distance in the Travelling Salesman Problem. Technical report CSD-950018, UCLA Computer Science Department"},{"key":"15_CR2","unstructured":"Boyan, J.A., Moore, A.W.: Learning Evaluation Functions for Global Optimization and Boolean Satisfiability. In: 15th National Conference on Artificial Intelligence and 10th Innovative Applications of Artificial Intelligence Conference, pp. 3\u201310. AAAI Press \/ MIT Press (1998)"},{"key":"15_CR3","first-page":"1017","volume-title":"Conference on Advance in Neural Information Processing Systems","author":"R. Crites","year":"1999","unstructured":"Crites, R., Barto, A.: Improving Elevator Performance Using Reinforcement Learning. In: Conference on Advance in Neural Information Processing Systems, pp. 1017\u20131023. MIT Press, Cambridge (1999)"},{"key":"15_CR4","unstructured":"Gagliolo, M., Schmidhuber, J.: Gambling in a Computationally Expensive Casino: Algorithm Selection as a Bandit Problem. In: Online Trading of Exploration and Exploitation, NIPS 2006 Workshop, Whistler, BC, Canada (2006)"},{"key":"15_CR5","first-page":"252","volume-title":"12th International Conference on Machine Learning","author":"L.M. Gambardella","year":"1995","unstructured":"Gambardella, L.M., Dorigo, M.: Ant-Q: A Reinforcement Learning Approach to the Traveling Salesman Problem. In: 12th International Conference on Machine Learning, pp. 252\u2013260. Morgan Kaufmann, San Francisco (1995)"},{"key":"15_CR6","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1613\/jair.7","volume":"1","author":"I.P. Gent","year":"1993","unstructured":"Gent, I.P., Walsh, T.: An Empirical Analysis of Search in GSAT. Journal of Artificial Intelligence Research\u00a01, 47\u201359 (1993)","journal-title":"Journal of Artificial Intelligence Research"},{"key":"15_CR7","first-page":"73","volume-title":"Hybrid Problems, Hybrid Solutions","author":"I.P. Gent","year":"1995","unstructured":"Gent, I.P., Walsh, T.: Unsatisfied Variables in Local Search. In: Hallam, J. (ed.) Hybrid Problems, Hybrid Solutions, pp. 73\u201385. IOS Press, Amsterdam (1995)"},{"key":"15_CR8","volume-title":"Stochastic Local Search: Foundations and Applications","author":"H.H. Hoos","year":"2004","unstructured":"Hoos, H.H., St\u00fctzle, T.: Stochastic Local Search: Foundations and Applications. Morgan Kaufmann, San Francisco (2004)"},{"key":"15_CR9","first-page":"511","volume-title":"17th International Conference on Machine Learning","author":"M.G. Lagoudakis","year":"2000","unstructured":"Lagoudakis, M.G., Littman, M.L.: Algorithm Selection Using Reinforcement Learning. In: 17th International Conference on Machine Learning, pp. 511\u2013518. Morgan Kaufmann, San Francisco (2000)"},{"key":"15_CR10","first-page":"159","volume":"22","author":"S. Mahadevan","year":"1996","unstructured":"Mahadevan, S.: Average Reward Reinforcement Learning: Foundations, Algorithms, and Empirical Results. Machine Learning\u00a022, 159\u2013196 (1996)","journal-title":"Machine Learning"},{"key":"15_CR11","unstructured":"McAllester, D.A., Selman, B., Kautz, H.A.: Evidence for Invariants in Local Search. In: 14th National Conference on Artificial Intelligence and Ninth Innovative Applications of Artificial Intelligence Conference, pp. 321\u2013326. AAAI Press \/ MIT Press (1997)"},{"key":"15_CR12","first-page":"189","volume-title":"Congress on Evolutionary Computation","author":"V. Miagkikh","year":"1999","unstructured":"Miagkikh, V., Punch, W.: Global Search in Combinatorial Optimization using Reinforcement Learning Algorithms. In: Congress on Evolutionary Computation, vol.\u00a01, pp. 189\u2013196. IEEE, Los Alamitos (1999)"},{"key":"15_CR13","first-page":"1017","volume-title":"Advances in Neural Information Processing Systems 11","author":"R. Moll","year":"1999","unstructured":"Moll, R., Barto, A., Perkins, T., Sutton, R.: Learning Instance-Independent Value Functions to Enhance Local Search. In: Advances in Neural Information Processing Systems 11, pp. 1017\u20131023. MIT Press, Cambridge (1999)"},{"key":"15_CR14","unstructured":"Morris, P.: The Breakout Method for Escaping from Local Minima. In: 11th National Conference on Artificial Intelligence, pp. 40\u201345. AAAI Press \/ MIT Press (1993)"},{"key":"15_CR15","first-page":"523","volume-title":"Choosing Search Heuristics by Non-Stationary Reinforcement Learning. Metaheuristics: Computer Decision-Making","author":"A. Nareyek","year":"2004","unstructured":"Nareyek, A.: Choosing Search Heuristics by Non-Stationary Reinforcement Learning. Metaheuristics: Computer Decision-Making, pp. 523\u2013544. Kluwer, Dordrecht (2004)"},{"key":"15_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1007\/11499107_15","volume-title":"Theory and Applications of Satisfiability Testing","author":"S.D. Prestwich","year":"2005","unstructured":"Prestwich, S.D.: Random Walk With Continuously Smoothed Variable Weights. In: Bacchus, F., Walsh, T. (eds.) SAT 2005. LNCS, vol.\u00a03569, pp. 203\u2013215. Springer, Heidelberg (2005)"},{"key":"15_CR17","unstructured":"Rummery, G.A., Niranjan, M.: On-line Q-learning Using Connectionist Systems. Technical report CUED\/F-INFENG\/TR 166, Engineering Dept., Cambridge University, UK (1994)"},{"key":"15_CR18","first-page":"298","volume-title":"10th International Conference on Machine Learning","author":"A. Schwartz","year":"1993","unstructured":"Schwartz, A.: A Reinforcement Learning Method for Maximizing Undiscounted Rewards. In: 10th International Conference on Machine Learning, pp. 298\u2013305. Morgan Kaufmann, San Francisco (1993)"},{"key":"15_CR19","first-page":"337","volume-title":"12th National Conference on Artificial Intelligence","author":"B. Selman","year":"1994","unstructured":"Selman, B., Kautz, H.A., Cohen, B.: Noise Strategies for Improving Local Search. In: 12th National Conference on Artificial Intelligence, pp. 337\u2013343. AAAI Press, Menlo Park (1994)"},{"key":"15_CR20","first-page":"284","volume-title":"Learning Without State-Estimation in Partially Observable Markovian Decision Processes. Eleventh International Conference on Machine Learning","year":"1994","unstructured":"Singh, S., Jaakkola, T., Jordan, M., Cohen, W.W., Hirsh, H. (eds.): Learning Without State-Estimation in Partially Observable Markovian Decision Processes. Eleventh International Conference on Machine Learning, pp. 284\u2013292. Morgan Kaufmann, San Francisco (1994)"},{"key":"15_CR21","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":"3","key":"15_CR22","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1145\/203330.203343","volume":"38","author":"G. Tesauro","year":"1995","unstructured":"Tesauro, G.: Temporal Difference Learning and TD-Gammon. Communications of the ACM\u00a038(3), 58\u201367 (1995)","journal-title":"Communications of the ACM"},{"key":"15_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1007\/3-540-44886-1_13","volume-title":"Advances in Artificial Intelligence","author":"D.A.D. Tompkins","year":"2003","unstructured":"Tompkins, D.A.D., Hoos, H.H.: Scaling and Probabilistic Smoothing: Dynamic Local Search for Unweighted MAX-SAT. In: Xiang, Y., Chaib-draa, B. (eds.) Canadian AI 2003. LNCS, vol.\u00a02671, pp. 145\u2013159. Springer, Heidelberg (2003)"},{"key":"15_CR24","unstructured":"Varrentrapp, K.E.: A Practical Framework for Adaptive Metaheuristics. PhD thesis, Fachgebiet Intellektik, Fachbereich Informatik, Technische Universit\u00e4t Darmstadt, Darmstadt, Germany (2005)"},{"key":"15_CR25","unstructured":"Watkins, C.J.C.H.: Learning From Delayed Rewards. PhD thesis. Cambridge University (1989)"},{"key":"15_CR26","first-page":"1114","volume-title":"14th International Joint Conference on Artificial Intelligence","author":"W. Zhang","year":"1995","unstructured":"Zhang, W., Dietterrich, T.D.: A Reinforcement Learning Approach to Job-Shop Scheduling. In: 14th International Joint Conference on Artificial Intelligence, pp. 1114\u20131120. Morgan Kaufmann, San Francisco (1995)"}],"container-title":["Lecture Notes in Computer Science","Learning and Intelligent Optimization"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-92695-5_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,3,4]],"date-time":"2019-03-04T13:20:53Z","timestamp":1551705653000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-92695-5_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008]]},"ISBN":["9783540926948","9783540926955"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-92695-5_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2008]]}}}