Scaling Behavior of the Evolution Strategy when Evolving Neuronal Control Architectures for Autonomous Agents

This paper presents the application of the evolution strategy to the evolution of different controllers for autonomous agents. Autonomous agents are embodied systems that behave in the real world without any human control. Most of the pertinent research has employed genetic algorithms. Epistatic interaction between the parameters of the fitness function is a well-known problem, since it drastically slows down genetic algorithms. The evolution strategy, however, performs rotationally invariant, because it applies gaussian mutations with a probability pm=1 to all parameters per offspring. This paper investigates the scaling behavior of the evolution strategy when evolving different neuronal control architectures for autonomous agents. The results demonstrate that the evolution strategy dramatically accelerates the development process, which is of great practical relevance, since the fitness evaluation of each controller takes approximately one minute on a physical robot.

[1]  Hans-Paul Schwefel,et al.  Evolution and optimum seeking , 1995, Sixth-generation computer technology series.

[2]  V. Braitenberg.  Vehicles, Experiments in Synthetic Psychology , 1984 .

[3]  Stewart W. Wilson,et al.  From Animals to Animats 5. Proceedings of the Fifth International Conference on Simulation of Adaptive Behavior , 1997 .

[4]  Rodney A. Brooks,et al.  A Robust Layered Control Syste For A Mobile Robot , 2022 .

[5]  Thomas Bäck,et al.  An Overview of Evolutionary Algorithms for Parameter Optimization , 1993, Evolutionary Computation.

[6]  Geoffrey E. Hinton,et al.  Proceedings of the 1988 Connectionist Models Summer School , 1989 .

[7]  R. Salomon.  Re-evaluating genetic algorithm performance under coordinate rotation of benchmark functions. A survey of some theoretical and practical aspects of genetic algorithms. , 1996, Bio Systems.

[8]  Stefano Nolfi,et al.  Learning to Adapt to Changing Environments in Evolving Neural Networks , 1996, Adapt. Behav..

[9]  Inman Harvey,et al.  Evolving visually guided robots , 1993 .

[10]  Ieee Robotics,et al.  IEEE journal of robotics and automation , 1985 .

[11]  Francesco Mondada,et al.  Evolution of homing navigation in a real mobile robot , 1996, IEEE Trans. Syst. Man Cybern. Part B.

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

[13]  Francesco Mondada,et al.  Evolution of Plastic Neurocontrollers for Situated Agents , 1996 .

[14]  Ralf Salomon,et al.  Performance Degradation of Genetic Algorithms under Coordinate Rotation , 1996, Evolutionary Programming.

[15]  Pattie Maes,et al.  Designing autonomous agents: Theory and practice from biology to engineering and back , 1990, Robotics Auton. Syst..