NEAT in HyperNEAT Substituted with Genetic Programming

In this paper we present application of genetic programming (GP) [1] to evolution of indirect encoding of neural network weights. We compare usage of original HyperNEAT algorithm with our implementation, in which we replaced the underlying NEAT with genetic programming. The algorithm was named HyperGP. The evolved neural networks were used as controllers of autonomous mobile agents (robots) in simulation. The agents were trained to drive with maximum average speed. This forces them to learn how to drive on roads and avoid collisions. The genetic programming lacking the NEAT complexification property shows better exploration ability and tends to generate more complex solutions in fewer generations. On the other hand, the basic genetic programming generates quite complex functions for weights generation. Both approaches generate neural controllers with similar abilities.

[1]  Edmund K. Burke,et al.  Parallel Problem Solving from Nature - PPSN IX: 9th International Conference, Reykjavik, Iceland, September 9-13, 2006, Proceedings , 2006, PPSN.

[2]  P. Durr,et al.  Evolvability of Neuromodulated Learning for Robots , 2008, 2008 ECSIS Symposium on Learning and Adaptive Behaviors for Robotic Systems (LAB-RS).

[3]  Miroslav Snorek,et al.  Hybrid Evolution of Heterogeneous Neural Networks , 2008, ICANN.

[4]  Dario Floreano,et al.  Neuroevolution with Analog Genetic Encoding , 2006, PPSN.

[5]  Jan Koutník,et al.  HyperNEAT controlled robots learn how to drive on roads in simulated environment , 2009, 2009 IEEE Congress on Evolutionary Computation.

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

[7]  M. Waibel.  Evolution of cooperation in artificial ants , 2007 .

[8]  Claudio Mattiussi,et al.  Evolutionary synthesis of analog networks , 2005 .

[9]  Peter J. Angeline,et al.  An evolutionary algorithm that constructs recurrent neural networks , 1994, IEEE Trans. Neural Networks.

[10]  Véra Kůrková,et al.  Artificial Neural Networks - ICANN 2008 , 18th International Conference, Prague, Czech Republic, September 3-6, 2008, Proceedings, Part I , 2008, ICANN.

[11]  Kenneth O. Stanley,et al.  Generative encoding for multiagent learning , 2008, GECCO '08.

[12]  Jürgen Schmidhuber,et al.  Training Recurrent Networks by Evolino , 2007, Neural Computation.

[13]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

[14]  Kenneth O. Stanley,et al.  Generating large-scale neural networks through discovering geometric regularities , 2007, GECCO '07.

[15]  Kenneth O. Stanley,et al.  A novel generative encoding for exploiting neural network sensor and output geometry , 2007, GECCO '07.