Numerical optimization with neuroevolution

Neuroevolution techniques have been successful in many sequential decision tasks, such as robot control and game playing. This paper aims at establishing whether they can be useful in numerical optimization more generally, by comparing neuroevolution to linear programming in a manufacturing optimization domain. It turns out that neuroevolution can learn to compensate for uncertainty in the data and outperform linear programming when the number of variables in the problem is small and the required precision is low, but the current techniques do not (yet) provide an advantage in problems where many variables must be optimized with high precision.

[1]  M. A. Stuchly,et al.  Electromagnetic System Design Using Genetic Algorithms , 1999 .

[2]  X. Yao.  Evolving Artificial Neural Networks , 1999 .

[3]  Dana H. Ballard,et al.  Interpolation coding: A representation for numbers in neural models , 1987, Biological Cybernetics.

[4]  Xin Yao,et al.  Evolving artificial neural networks , 1999, Proc. IEEE.

[5]  Jacques Periaux,et al.  Genetic Algorithms in Engineering and Computer Science , 1996 .

[6]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[7]  Risto Miikkulainen,et al.  Incremental Evolution of Complex General Behavior , 1997, Adapt. Behav..

[8]  L. Darrell Whitley,et al.  Cellular Encoding Applied to Neurocontrol , 1995, ICGA.

[9]  Risto Miikkulainen,et al.  Evolving Neural Networks through Augmenting Topologies , 2002, Evolutionary Computation.

[10]  L. Darrell Whitley,et al.  Genetic Reinforcement Learning for Neurocontrol Problems , 2004, Machine Learning.

[11]  Jeffrey L. Elman,et al.  Learning and Evolution in Neural Networks , 1994, Adapt. Behav..

[12]  Diego Calvanese,et al.  Unifying Class-Based Representation Formalisms , 2011, J. Artif. Intell. Res..

[13]  Risto Miikkulainen,et al.  Evolving Obstacle Avoidance Behavior in a Robot Arm , 1996 .

[14]  Risto Miikkulainen,et al.  Efficient evolution of neural network topologies , 2002, Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600).

[15]  John J. Grefenstette,et al.  Evolutionary Algorithms for Reinforcement Learning , 1999, J. Artif. Intell. Res..

[16]  George B. Dantzig,et al.  Linear programming and extensions , 1965 .

[17]  Chris Aldrich,et al.  Intelligent process control utilising symbiotic memetic neuro-evolution , 2002, Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600).

[18]  Inman Harvey,et al.  Evolving Recurrent Dynamical Networks for Robot Control , 1993 .

[19]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[20]  Risto Miikkulainen,et al.  Forming Neural Networks Through Efficient and Adaptive Coevolution , 1997, Evolutionary Computation.

[21]  Risto Miikkulainen,et al.  Solving Non-Markovian Control Tasks with Neuro-Evolution , 1999, IJCAI.

[22]  Risto Miikkulainen,et al.  Efficient Reinforcement Learning through Symbiotic Evolution , 1996, Machine Learning.

[23]  David B. Fogel,et al.  Blondie24: Playing at the Edge of AI , 2001 .

[24]  George B. Dantzig,et al.  Linear programming and extensions , 1965 .