Competitive and Co-Operative Analysis of Genetic-Programming

Abstract

Co-operative and competitive building blocks drive the evolution of GP. There exists useful schema which remains promising and persistent in terms of their occurrence over the generations. These schemas are majorly present at levels other than root level, and gradually this genetic material is pushed towards the root level by co-operation, where they compete with each other, few among those increase their occurrence at the root level and rest vanished. These schemas if extended to the deeper depths, still be useful and helps in achieving the goal of the problem. Lastly, some of these schemas are same even in different runs for the same problem. The experiment results show that the evolution is driven by co-operative rooted building blocks as well, along with the competitive building blocks. It shows the count of building blocks in different positions never reaches zero, which indicates the presence of the genetic material required for the construction of the building block at a particular position in the form of co-operation and competition with other schemas, which, at a later stage, may move to the correct position (root level). In our work, these behaviours are also demonstrated by injecting genetic material manually in the population and investigated their prominence throughout the evolution. This work contributes to many dimensions like; by combining these competitive building blocks appear at root level uncovers the problem solution over time. For that reason, by identifying, preserving and exchanging these building blocks explicitly, the system enactment can be improved severely. Additionally, the solutions of the developed versions of the same problem can also be handled through this.