A Novel Biologically Inspired Developmental Indirect Encoding for the Evolution of Neural Network Controllers for Autonomous Agents

Evolutionary algorithms provide the ability to automatically design robot controllers, but their wider use is hampered by a number of problems, including the difficulty of obtaining complex behaviors. This paper proposes a biologically inspired indirect encoding method for developing neural networks that control autonomous agents. The model is divided into three stages, the first two stages determine the structure of the network – the positions of the neurons and the network connectivity, and the third stage, occurring during the lifetime of the agent, determines the strength of connections based on the network activity. The model was tested experimentally by simulating an agent in an artificial environment, and the results of these simulations show that the method successfully evolved agents, capable of distinguishing between several types of objects, collecting some while avoiding others, without the use of a complex fitness function.

[1]  Jean-Arcady Meyer,et al.  Evolution and development of neural controllers for locomotion, gradient-following, and obstacle-avoidance in artificial insects , 1998, IEEE Trans. Neural Networks.

[2]  Kenneth O. Stanley,et al.  Abandoning Objectives: Evolution Through the Search for Novelty Alone , 2011, Evolutionary Computation.

[3]  J. Bongard,et al.  Evolving Monolithic Robot Controllers through Incremental Shaping , 2011 .

[4]  Hugo de Garis.  The Genetic Programming of an Artificial Nervous System , 1991 .

[5]  R. Beer,et al.  20 – A developmental model for the evolution of complete autonomous agents , 2003 .

[6]  Jean-Arcady Meyer,et al.  Incremental Evolution of Target-Following Neuro-controllers for Flapping-Wing Animats , 2006, SAB.

[7]  M. P. van den Heuvel,et al.  The Ontogeny of the Human Connectome , 2013, The Neuroscientist : a review journal bringing neurobiology, neurology and psychiatry.

[8]  Randall D. Beer,et al.  On the Dynamics of Small Continuous-Time Recurrent Neural Networks , 1995, Adapt. Behav..

[9]  Malachy Eaton,et al.  Evolutionary Humanoid Robotics , 2015, SpringerBriefs in Intelligent Systems.

[10]  Milena Lazarova,et al.  AN EVOLUTIONARY APPROACH TO THE DESIGN OF CONVOLUTIONAL NEURAL NETWORKS FOR HUMAN ACTIVITY RECOGNITION , 2021 .

[11]  W. Greenough,et al.  Experience and brain development. , 1987, Child development.

[12]  Li-Huei Tsai,et al.  Trekking across the Brain: The Journey of Neuronal Migration , 2007, Cell.

[13]  Wofgang Maas,et al.  Networks of spiking neurons: the third generation of neural network models , 1997 .

[14]  Frédéric Gruau,et al.  Automatic Definition of Modular Neural Networks , 1994, Adapt. Behav..

[15]  D. Parisi,et al.  Phenotypic plasticity in evolving neural networks , 1994, Proceedings of PerAc '94. From Perception to Action.