Runtime Analysis of (1+1) Evolutionary Algorithm Controlled with Q-learning Using Greedy Exploration Strategy on OneMax+ZeroMax Problem

There exist optimization problems with the target objective, which is to be optimized, and several extra objectives. The extra objectives may or may not be helpful in optimization process in terms of the number of objective evaluations necessary to reach an optimum of the target objective.

[1]  Mikkel T. Jensen,et al.  Helper-objectives: Using multi-objective evolutionary algorithms for single-objective optimisation , 2004, J. Math. Model. Algorithms.

[2]  Frank Neumann,et al.  On the Effects of Adding Objectives to Plateau Functions , 2009, IEEE Transactions on Evolutionary Computation.

[3]  Frank W. Ciarallo,et al.  Helper-objective optimization strategies for the Job-Shop Scheduling Problem , 2011, Appl. Soft Comput..

[4]  Arina Buzdalova,et al.  A First Step towards the Runtime Analysis of Evolutionary Algorithm Adjusted with Reinforcement Learning , 2013, 2013 12th International Conference on Machine Learning and Applications.

[5]  B. Hajek.  Hitting-time and occupation-time bounds implied by drift analysis with applications , 1982, Advances in Applied Probability.

[6]  Carsten Witt,et al.  Optimizing Linear Functions with Randomized Search Heuristics - The Robustness of Mutation , 2012, STACS.

[7]  Richard A. Watson,et al.  Reducing Local Optima in Single-Objective Problems by Multi-objectivization , 2001, EMO.

[8]  Ingo Wegener,et al.  Can Single-Objective Optimization Profit from Multiobjective Optimization? , 2008, Multiobjective Problem Solving from Nature.

[9]  Joshua D. Knowles,et al.  Multiobjectivization by Decomposition of Scalar Cost Functions , 2008, PPSN.

[10]  Arina Buzdalova,et al.  Increasing Efficiency of Evolutionary Algorithms by Choosing between Auxiliary Fitness Functions with Reinforcement Learning , 2012, 2012 11th International Conference on Machine Learning and Applications.

[11]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[12]  Kalyanmoy Deb,et al.  Multiobjective Problem Solving from Nature: From Concepts to Applications , 2008, Natural Computing Series.