Using promoters and functional introns in genetic algorithms for neuroevolutionary learning in non-stationary problems

This paper addresses the problem of adaptive learning in non-stationary problems through neuroevolution. It is a general problem that is very relevant in many tasks, for example, in the context of robot model learning from interaction with the world. Traditional learning algorithms fail in this task as they have mostly been designed for learning a single model in a static setting. Neuroevolutionary techniques have obtained promising results in this non-stationary context but are still lacking in certain types of problems, especially those dealing with information streams where different portions correspond to different models. An extension through the introduction of the concept of introns and promoter genes enables neuroevolutionary algorithms to improve their performance on this type of problems. Following this approach, an implementation of these concepts on a genetic algorithm for neuroevolution is presented here. This algorithm is called promoter based genetic algorithm (PBGA) and it uses a genotypic representation with a set of features that allows for an intrinsic memory in the population that is self-regulated, in the sense that functional parts of the individuals are preserved through generations without an explicit knowledge about the number of different tasks or models that have to arise from the data stream. Some illustrative tests of the potential of these techniques based on the continuous switch between completely different objective functions that must be learnt are presented and the results are analyzed and compared to other neuroevolutionary algorithms.

[1]  Hajime Kita,et al.  Adaptation to Changing Environments by Means of the Memory Based Thermodynamical Genetic Algorithm , 1997, ICGA.

[2]  David E. Goldberg,et al.  Nonstationary Function Optimization Using Genetic Algorithms with Dominance and Diploidy , 1987, ICGA.

[3]  Jonathan A. Wright,et al.  Self-adaptive fitness formulation for constrained optimization , 2003, IEEE Trans. Evol. Comput..

[4]  Zbigniew Michalewicz,et al.  Evolutionary Approach to Non-stationary Optimisation Tasks , 1999, ISMIS.

[5]  Dipankar Dasgupta,et al.  Nonstationary Function Optimization using the Structured Genetic Algorithm , 1992, PPSN.

[6]  Kok Cheong Wong,et al.  A New Diploid Scheme and Dominance Change Mechanism for Non-Stationary Function Optimization , 1995, ICGA.

[7]  J. Eggermont.  Non-stationary Fun tion Optimization using Evolutionary Algorithms with a Case-based Memory , 2007 .

[8]  Helen G. Cobb,et al.  An Investigation into the Use of Hypermutation as an Adaptive Operator in Genetic Algorithms Having Continuous, Time-Dependent Nonstationary Environments , 1990 .

[9]  David E. Moriarty,et al.  Symbiotic Evolution of Neural Networks in Sequential Decision Tasks , 1997 .

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

[11]  Conor Ryan,et al.  Non-stationary Function Optimization using Polygenic Inheritance , 1999, GECCO.

[12]  Risto Miikkulainen,et al.  Efficient Non-linear Control Through Neuroevolution , 2006, ECML.

[13]  W. Jacak,et al.  Genetic algorithm based neural networks for dynamical system modeling , 1995, Proceedings of 1995 IEEE International Conference on Evolutionary Computation.

[14]  Hajime Kita,et al.  Adaptation to a Changing Environment by Means of the Feedback Thermodynamical Genetic Algorithm , 1996, PPSN.

[15]  D. R. McGregor,et al.  Designing application-specific neural networks using the structured genetic algorithm , 1992, [Proceedings] COGANN-92: International Workshop on Combinations of Genetic Algorithms and Neural Networks.

[16]  Larry D. Pyeatt,et al.  A comparison between cellular encoding and direct encoding for genetic neural networks , 1996 .

[17]  Risto Miikkulainen,et al.  Retaining Learned Behavior During Real-Time Neuroevolution , 2005, AIIDE.

[18]  Pavel Brazdil,et al.  Proceedings of the European Conference on Machine Learning , 1993 .

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

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

[21]  Jürgen Branke,et al.  Memory enhanced evolutionary algorithms for changing optimization problems , 1999, Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406).

[22]  Hillol Kargupta,et al.  Function induction, gene expression, and evolutionary representation construction , 1999 .

[23]  Hajime Kita,et al.  Adaptation to a Changing Environment by Means of the Thermodynamical Genetic Algorithm , 1999 .