A Compass to Guide Genetic Algorithms

Proceedings of the 11th Annual Conference on Genetic and Evolutionary Computation

Sebag

2009

One 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 (AOS) methods, i.e., techniques that automatically select the operator to be applied among the available ones, while searching for the solution. Four previously published operator selection rules are combined to four different credit assignment mechanisms. These 16 AOS combinations are analyzed and compared in the light of two wellknown benchmark problems in Evolutionary Computation, the Royal Road and the Long K-Path.

“…Along this line, [25] proposed another credit measure called Compass, defined as a weighted sum of fitness improvement (intensification) and offspring diversity (diversification).…”

Section: Credit Assignmentmentioning

confidence: 99%

Analysis of adaptive operator selection techniques on the royal road and long k-path problems

Proceedings of the 11th Annual Conference on Genetic and Evolutionary Computation

Sebag

2009

“…Along this line, [33] proposed another credit measure called Compass, defined as a weighted sum of fitness improvement (intensification) and offspring diversity (diversification). In [32], a different aggregation between both impact measures was proposed, based on the Pareto Dominance paradigm.…”

Section: Credit Assignmentmentioning

confidence: 99%

“…In essence, the goal of Adaptive Operator Selection is to select on the fly the operator 1 that maximizes some measure of quality, usually, though not exclusively [33,31], reflecting the fitness improvement brought by its application. Adaptive Operator Selection thus raises two main issues.…”

Section: Introductionmentioning

confidence: 99%

Analyzing bandit-based adaptive operator selection mechanisms

Costa

et al. 2010

Ann Math Artif Intell

135

123

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 the rewards are mainly based on the fitness improvement brought by the corresponding operator to the individual it is applied to. However, the AOS problem is dynamic, whereas standard MAB algorithms are known to optimally solve the exploitation versus exploration trade-off in static settings. An original dynamic variant of the standard MAB Upper Confidence Bound algorithm is proposed here, using a sliding time window to compute both its exploitation and exploration terms. In order to perform sound comparisons between AOS algorithms, artificial scenarios have been proposed in the literature. They are extended here toward smoother transitions between different reward settings. The resulting original testbed also includes a real evolutionary algorithm that is applied to the well-known Royal Road problem. It is used here to perform a thorough analysis of the behavior of AOS algorithms, to assess their sensitivity with respect to their own hyper-parameters, and to propose a sound comparison of their performances.

“…Typically in multi-modal search landscapes, population diversity is equally important; it must mandatorily be preserved in order to avoid premature convergence to local optima. Based on this remark, the socalled Compass credit assignment [20] measures the operator ability to produce more fit individuals while preserving the population diversity.…”

Section: Credit Assignmentmentioning

confidence: 99%

“…During each exploration phase, operators are uniformly selected and their rewards are estimated; during the following exploitation phase, operators are selected according to their reward. The fraction of generations devoted to exploration phases (circa 25 % in [24]) is meant to catch up with the changes in the reward distribution; unfortunately, it severely harms the population and the progress of evolution whenever disruptive operators are considered [20].…”

Section: Operator Selection Rulesmentioning

confidence: 99%

Dynamic Multi-Armed Bandits and Extreme Value-Based Rewards for Adaptive Operator Selection in Evolutionary Algorithms

Costa

Lecture Notes in Computer Science

et al. 2009

Abstract. The performance of many efficient algorithms critically depends on the tuning of their parameters, which on turn depends on the problem at hand. For example, the performance of Evolutionary Algorithms critically depends on the judicious setting of the operator rates. The Adaptive Operator Selection (AOS) heuristic that is proposed here rewards each operator based on the extreme value of the fitness improvement lately incurred by this operator, and uses a Multi-Armed Bandit (MAB) selection process based on those rewards to choose which operator to apply next. This Extreme-based Multi-Armed Bandit approach is experimentally validated against the Average-based MAB method, and is shown to outperform previously published methods, whether using a classical Average-based rewarding technique or the same Extreme-based mechanism. The validation test suite includes the easy One-Max problem and a family of hard problems known as "Long k-paths".