Upper Confidence Bound (UCB) Algorithms for Adaptive Operator Selection in MOEA/D

详细信息    查看全文

• 关键词：Adaptive Operator Selection (AOS) ; MOEA/D ; Upper Confidence Bound (UCB) Algorithms ; UCB1 ; UCB ; Tuned ; UCB ; V
• 刊名：Lecture Notes in Computer Science
• 出版年：2015
• 出版时间：2015
• 年：2015
• 卷：9018
• 期：1
• 页码：411-425
• 全文大小：259 KB
• 参考文献：1. Auer, P (2003) Using confidence bounds for exploitation-exploration trade-offs. J. Mach. Learn. Res. 3: pp. 397-422
  2. Auer, P, Cesa-Bianchi, N, Fischer, P (2002) Finite-time analysis of the multiarmed bandit problem. Mach. Learn. 47: pp. 235-256 CrossRef
  3. Conover, W.J.: Practical Nonparametric Statistics, 3rd edn. Wiley (1999)
  4. Ehrgott, M (2006) A discussion of scalarization techniques for multiple objective integer programming. Ann. Oper. Res. 147: pp. 343-360 CrossRef
  5. Fialho, A.: Adaptive operator selection for optimization. Ph.D. thesis, Comput. Sci. Dept. - Univ. Paris-Sud XI (2010)
  6. Fialho, A., Schoenauer, M., Sebag, M.: Analysis of adaptive operator selection techniques on the royal road and long k-path problems. In: Conference on Genetic and Evolutionary Computation, pp. 779-86 (2009)
  7. Goldberg, DE (1990) Probability matching, the magnitude of reinforcement, and classifier system bidding. Mach. Learn. 5: pp. 407-425
  8. Gong, W, Fialho, l, Cai, Z, Li, H (2011) Adaptive strategy selection in differential evolution for numerical optimization: An empirical study. Inform. Sciences 181: pp. 5364-5386 CrossRef
  9. Mashwani, Khan (2012) W., Salhi, A.: A decomposition-based hybrid multiobjective evolutionary algorithm with dynamic resource allocation. Appl. Soft Comput. 12: pp. 2765-2780 CrossRef
  10. Knowles, J., Thiele, L., Zitzler, E.: A Tutorial on the Performance Assessment of Stochastic Multiobjective Optimizers. TIK Report 214, Computer Engineering and Networks Laboratory (TIK), ETH Zurich (February 2006)
  11. Li, K, Fialho, A, Kwong, S, Zhang, Q (2014) Adaptive operator selection with bandits for a multiobjective evolutionary algorithm based on decomposition. IEEE Transactions on Evolutionary Computation 18: pp. 114-130 CrossRef
  12. Sato, H.: Inverted PBI in MOEA/D and its impact on the search performance on multi and many-objective optimization. In: Proceedings of the 2014 Conference on Genetic and Evolutionary Computation, GECCO 2014, pp. 645-52. ACM, New York (2014). http://doi.acm.org/10.1145/2576768.2598297
  13. Thierens, D.: An adaptive pursuit strategy for allocating operator probabilities. In: Conference on Genetic and Evolutionary Computation, pp. 1539-546 (2005)
  14. Venske, S.M., Gonalves, R.A., Delgado, M.R.: ADEMO/D: Multiobjective optimization by an adaptive differential evolution algorithm. Neurocomputing 127, 65-7 (2014), advances in Intelligent Systems Selected papers from the 2012 Brazilian Symposium on Neural Networks
  15. Zhang, Q., Zhou, A., Zhao, S., Suganthan, P.N., Liu, W., Tiwari, S.: Multiobjective optimization test instances for the CEC 2009 special session and competition. Tech. rep., University of Essex and Nanyang Technological University, CES-487 (2008)
  16. Zhang, Q., Liu, W., Li, H.: The performance of a new version of MOEA/D on CEC09 unconstrained mop test instances. In: IEEE Congress on Evolutionary Computation, CEC 2009, pp. 203-08 (May 2009)
  17. Zhao, SZ, Suganthan, PN, Zhang, Q (2012) Decomposition-based multiobjective evolutionary algorithm with an ensemble of neighborhood sizes. IEEE Trans. Evol. Comput. 16: pp. 442-446 CrossRef
  
• 作者单位：Evolutionary Multi-Criterion Optimization
• 丛书名：978-3-319-15933-1
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349

文摘

Adaptive Operator Selection (AOS) is a method used to dynamically determine which operator should be applied in an optimization algorithm based on its performance history. Recently, Upper Confidence Bound (UCB) algorithms have been successfully applied for this task. UCB algorithms have special features to tackle the Exploration versus Exploitation (EvE) dilemma presented on the AOS problem. However, it is important to note that the use of UCB algorithms for AOS is still incipient on Multiobjective Evolutionary Algorithms (MOEAs) and many contributions can be made. The aim of this paper is to extend the study of UCB based AOS methods. Two methods are proposed: MOEA/D-UCB-Tuned and MOEA/D-UCB-V, both use the variance of the operators-rewards in order to obtain a better EvE tradeoff. In these proposals the UCB-Tuned and UCB-V algorithms from the multiarmed bandit (MAB) literature are combined with MOEA/D (MOEA based on decomposition), one of the most successful MOEAs. Experimental results demonstrate that MOEA/D-UCB-Tuned can be favorably compared with state-of-the-art adaptive operator selection MOEA/D variants based on probability (ENS-MOEA/D and ADEMO/D) and multi-armed bandits (MOEA/D-FRRMAB) methods.