ABSTRACT
The performance of evolutionary algorithms is highly affected by the selection of the variation operators to solve the problem at hand. This abstract presents a survey of results that have been obtained using the "Extreme - Dynamic Multi-Armed Bandit" (Ex-DMAB), a technique used to automatically select the operator to be applied between the available ones, while searching for the solution. Experiments on three well-known artificial problems of the EC community are presented, namely the OneMax, the long k-path and the Royal Road, demonstrating some improvements over both any choice of a single-operator alone, and the naive uniform choice of one operator at each application. The Ex-DMAB approach is also compared to the optimal choice of operators, whenever available. The results are discussed in the light of the new parameters that are introduced to tune the selection technique...
- ]]P. Auer, N. Cesa-Bianchi, and P. Fischer. Finite-time analysis of the multiarmed bandit problem. Machine Learning, 47(2/3):235--256, 2002. Google ScholarDigital Library
- ]]H. J. C. Barbosa and A. M. S´a. On adaptive operator probabilities in real coded genetic algorithms. In Proc. Intl. Conf. Chilean Computer Science Society, 2000.Google Scholar
- ]]M. Birattari, T. Stutzle, L. Paquete, and K. Varrentrapp. A racing algorithm for configuring metaheuristics. In Proc. GECCO, pages 11--18. Morgan Kaufmann, 2002.Google Scholar
- ]]L. Da Costa, A. Fialho, M. Schoenauer, and M. Sebag. Adaptive operator selection with dynamic multi-armed bandits. In Proc. GECCO, pages 913--920. ACM Press, 2008. Google ScholarDigital Library
- ]]L. Davis. Adapting operator probabilities in genetic algorithms. In Proc. ICGA, pages 61--69. Morgan Kaufmann, 1989. Google ScholarDigital Library
- ]]A. Fialho, L. Da Costa, M. Schoenauer, and M. Sebag. Extreme value based adaptive operator selection. In Proc. PPSN X, pages 175--184. Springer, 2008.Google Scholar
- ]]A. Fialho, L. DaCosta, M. Schoenauer, and M. Sebag. Dynamic multi-armed bandits and extreme value-based rewards for adaptive operator selection. In Proc. LION-3. Springer-Verlag, 2009. Google ScholarDigital Library
- ]]A. Fialho, M. Schoenauer, and M. Sebag. Analysis of adaptive operator selection techniques on the royal road and long k-path problems. In G. R. et al., editor, GECCO'09: Proceedings of the 11th Annual Conference on Genetic and Evolutionary Computation. ACM, July 2009 (to appear). Google ScholarDigital Library
- ]]D. Goldberg. Probability Matching, the Magnitude of Reinforcement, and Classifier System Bidding. Machine Learning, 5(4):407--426, 1990. Google ScholarDigital Library
- ]]C. Hartland, N. Baskiotis, S. Gelly, O. Teytaud, and M. Sebag. Change point detection and meta-bandits for online learning in dynamic environments. In Proc. CAp'07, July 2007.Google Scholar
- ]]B. A. Julstrom. What have you done for me lately? Adapting Operator Probabilities in a Steady-State Genetic Algorithms. In Proc. ICGA, pages 81--87. Morgan Kaufmann, 1995. Google ScholarDigital Library
- ]]F. Lobo and D. Goldberg. Decision making in a hybrid genetic algorithm. In Proc. ICEC'97, pages 121--125. IEEE Press, 1997.Google ScholarCross Ref
- ]]J. Maturana, A. Fialho, F. Saubion, M. Schoenauer, and M. Sebag. Extreme compass and dynamic multi-armed bandits for adaptive operator selection. In CEC'09: Proceedings of the IEEE International Conference on Evolutionary Computation (to appear). IEEE, 2009. Google ScholarDigital Library
- ]]J. Maturana and F. Saubion. A compass to guide genetic algorithms. In Proc. PPSN X, pages 256--265. Springer, 2008.Google Scholar
- ]]E. Page. Continuous inspection schemes. Biometrika, 41:100--115, 1954.Google ScholarCross Ref
- ]]D. Thierens. An adaptive pursuit strategy for allocating operator probabilities. In H.-G. Beyer, editor, Proc. GECCO'05, pages 1539--1546. ACM Press, 2005. Google ScholarDigital Library
- ]]A. Tuson and P. Ross. Adapting operator settings in genetic algorithms. Evolutionary Computation, 6(2):161--184, 1998. Google ScholarDigital Library
- ]]J. M. Whitacre, T. Q. Pham, and R. A. Sarker. Use of statistical outlier detection method in adaptive evolutionary algorithms. In M. Cattolico, editor, Proc. GECCO'06, pages 1345--1352. ACM, 2006. Google ScholarDigital Library
- ]]Wong, Lee, Leung, and Ho. A novel approach in parameter adaptation and diversity maintenance for GAs. Soft Computing, 7(8):506--515, 2003.Google ScholarDigital Library
Index Terms
- Extreme: dynamic multi-armed bandits for adaptive operator selection
Recommendations
Toward comparison-based adaptive operator selection
GECCO '10: Proceedings of the 12th annual conference on Genetic and evolutionary computationAdaptive Operator Selection (AOS) turns the impacts of the applications of variation operators into Operator Selection through a Credit Assignment mechanism. However, most Credit Assignment schemes make direct use of the fitness gain between parent and ...
Analysis of adaptive operator selection techniques on the royal road and long k-path problems
GECCO '09: Proceedings of the 11th Annual conference on Genetic and evolutionary computationOne of the choices that most affect the performance of Evolutionary Algorithms is the selection of the variation operators that are efficient to solve the problem at hand. This work presents an empirical analysis of different Adaptive Operator Selection ...
Analyzing bandit-based adaptive operator selection mechanisms
Several techniques have been proposed to tackle the Adaptive Operator Selection (AOS) issue in Evolutionary Algorithms. Some recent proposals are based on the Multi-armed Bandit (MAB) paradigm: each operator is viewed as one arm of a MAB problem, and ...
Comments