{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T11:24:34Z","timestamp":1725708274524},"publisher-location":"Berlin, Heidelberg","reference-count":11,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642351006"},{"type":"electronic","value":"9783642351013"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-35101-3_53","type":"book-chapter","created":{"date-parts":[[2012,11,29]],"date-time":"2012-11-29T11:40:16Z","timestamp":1354189216000},"page":"626-636","source":"Crossref","is-referenced-by-count":5,"title":["An Empirical Comparison of Two Common Multiobjective Reinforcement Learning Algorithms"],"prefix":"10.1007","author":[{"given":"Rustam","family":"Issabekov","sequence":"first","affiliation":[]},{"given":"Peter","family":"Vamplew","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"53_CR1","doi-asserted-by":"crossref","unstructured":"Barrett, L., Narayanan, S.: Learning all optimal policies with multiple criteria. In: Proceedings of the International Conference on Machine Learning (2008)","DOI":"10.1145\/1390156.1390162"},{"key":"53_CR2","first-page":"325","volume-title":"IFAC Workshop on Modeling and Control in Environmental Issues","author":"A. Castelletti","year":"2002","unstructured":"Castelletti, A., Corani, G., Rizzolli, A., Soncinie-Sessa, R., Weber, E.: Reinforcement learning in the operational management of a water system. In: IFAC Workshop on Modeling and Control in Environmental Issues, pp. 325\u2013330. Keio University, Yokohama (2002)"},{"key":"53_CR3","unstructured":"Gabor, Z., Kalmar, Z., Szepesvari, C.: Multi-criteria reinforcement learning. In: The Proceedings of the 15th International Conference on Machine Learning, pp. 197\u2013205 (1998)"},{"key":"53_CR4","series-title":"LNAI","doi-asserted-by":"publisher","first-page":"646","DOI":"10.1007\/11871842_63","volume-title":"Machine Learning: ECML 2006","author":"P. Geibel","year":"2006","unstructured":"Geibel, P.: Reinforcement Learning for MDPs with Constraints. In: F\u00fcrnkranz, J., Scheffer, T., Spiliopoulou, M. (eds.) ECML 2006. LNCS (LNAI), vol.\u00a04212, pp. 646\u2013653. Springer, Heidelberg (2006)"},{"key":"53_CR5","unstructured":"Mannor, S., Shimkin, N.: The steering approach for multi-criteria reinforcement learning. In: Neural Information Processing Systems, Vancouver, Canada, pp. 1563\u20131570 (2001)"},{"key":"53_CR6","doi-asserted-by":"crossref","unstructured":"Natarajan, S., Tadepalli, P.: Dynamic preferences in multi-criteria reinforcement learning. In: The Proceedings of the International Conference on Machine Learning, Bonn, Germany, pp. 601\u2013608 (2005)","DOI":"10.1145\/1102351.1102427"},{"key":"53_CR7","first-page":"2133","volume":"10","author":"B. Tanner","year":"2009","unstructured":"Tanner, B., White, A.: RL-Glue: Language-Independent Software for Reinforcement-Learning Experiments. Journal of Machine Learning Research\u00a010, 2133\u20132136 (2009)","journal-title":"Journal of Machine Learning Research"},{"issue":"1-2","key":"53_CR8","first-page":"51","volume":"84","author":"P. Vamplew","year":"2011","unstructured":"Vamplew, P., Dazeley, R., Berry, A., Issabekov, R., Dekker, E.: Empirical Evaluation Methods for Multiobjective Reinforcement Learning Algorithms. Machine Learning, Special Issue on Empirical Evaluation of Reinforcement Learning\u00a084(1-2), 51\u201380 (2011)","journal-title":"Machine Learning, Special Issue on Empirical Evaluation of Reinforcement Learning"},{"key":"53_CR9","unstructured":"While, L., Bradstreet, L., Barone, L.: A Fast Way of Calculating Exact Hypervolumes. IEEE Transactions on Evolutionary Computation (2010)"},{"issue":"10","key":"53_CR10","doi-asserted-by":"publisher","first-page":"1447","DOI":"10.1016\/j.neunet.2008.09.013","volume":"21","author":"E. Uchibe","year":"2008","unstructured":"Uchibe, E., Doya, K.: Finding intrinsic rewards by embodied evolution and constrained reinforcement learning. Neural Networks\u00a021(10), 1447\u20131455 (2008)","journal-title":"Neural Networks"},{"key":"53_CR11","unstructured":"Zitzler, E.: Evolutionary Algorithms for Multiobjective Optimization: Methods and Applications. PhD thesis, Swiss Federal Institute of Technology (ETH), Zurich, Switzerland (November 1999)"}],"container-title":["Lecture Notes in Computer Science","AI 2012: Advances in Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-35101-3_53","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,9]],"date-time":"2019-05-09T05:54:53Z","timestamp":1557381293000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-35101-3_53"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642351006","9783642351013"],"references-count":11,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-35101-3_53","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2012]]}}}