Coevolution of intelligent agents using cartesian genetic programming

Abstract

A coevolutionary competitive learning environment for two antagonistic agents is presented. The agents are controlled by a new kind of computational network based on a compartmentalised model of neurons. The genetic basis of neurons is an important [27] and neglected aspect of previous approaches. Accordingly, we have defined a collection of chromosomes representing various aspects of the neuron: soma, dendrites and axon branches, and synaptic connections. Chromosomes are represented and evolved using a form of genetic programming (GP) known as Cartesian GP. The network formed by running the chromosomal programs, has a highly dynamic morphology in which neurons grow, and die, and neurite branches together with synaptic connections form and change in response to environmental interactions. The idea of this paper is to demonstrate the importance of the genetic transfer of learned experience and life time learning. The learning is a consequence of the complex dynamics produced as a result of interaction (coevolution) between two intelligent agents. Our results show that both agents exhibit interesting learning capabilities.

A Survey of Self Modifying Cartesian Genetic Programming

“…Although CGP has been used in various ways in developmental systems Miller and Thomson, 2003;Khan et al, 2007), the programs that it produces are not themselves developmental. Instead, these approaches used a fixed length genotype to represent the programs defining the behaviour of cells.…”

Evolution, development and learning using self-modifying cartesian genetic programming

“…However, natural evolution does not work in this way, instead evolution operates at the very much lower level of genetic code and learning in organisms is an emergent consequence of many underlying processes and interactions with an external environment. The essential point here is that all learning occurs in the lifetime of the organism, a fact recently emphasized in [4,5]. From the point of view of this paper, the key point is that evolution has invented learning algorithms (inasmuch as physical learning processes can be simulated by algorithms).…”

Breaking the Synaptic Dogma: Evolving a Neuro-inspired Developmental Network

“…In order to evaluate the eectiveness of this approach we have previously applied it to a classic AI problem called wumpus world [5]. We found that the agents improved with experience and exhibited a range of intelligent behaviours.…”