论文信息 - Choosing Best Fitness Function with Reinforcement Learning

Choosing Best Fitness Function with Reinforcement Learning

This paper describes an optimization problem with one target function to be optimized and several supporting functions that can be used to speed up the optimization process. A method based on reinforcement learning is proposed for choosing a good supporting function during optimization using genetic algorithm. Results of applying this method to a model problem are shown.

Arina Buzdalova | Maxim Buzdalov

[1] Paulo Martins Engel,et al. Dealing with non-stationary environments using context detection , 2006, ICML.

[2] Maxim Buzdalov,et al. Generation of tests for programming challenge tasks using evolution algorithms , 2011, GECCO.

[3] E. Polak,et al. On Multicriteria Optimization , 1976 .

[4] Andrew W. Moore,et al. Reinforcement Learning: A Survey , 1996, J. Artif. Intell. Res..

[5] Dorothea Heiss-Czedik,et al. An Introduction to Genetic Algorithms. , 1997, Artificial Life.

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

[7] Lihong Li,et al. PAC model-free reinforcement learning , 2006, ICML.