Symbiogenesis in learning classifier systems

Symbiosis is the phenomenon in which organisms of different species live to gether in close association, resulting in a raised level of fitness for one or more of the organisms. Symbiogenesis is the name given to the process b y which symbiotic partners combine and unify, that is, become genetically l inked, giving rise to new morphologies and physiologies evolutionarily more advanced than their constituents. The importance of this process in the ev olution of complexity is now well established. Learning classifier systems are a machine learning technique that uses both evolutionary computing tech niques and reinforcement learning to develop a population of cooperative ru les to solve a given task. In this article we examine the use of symbiogene sis within the classifier system rule base to improve their performance. Re sults show that incorporating simple rule linkage does not give any benefit s. The concept of (temporal) encapsulation is then added to the symbiotic r ules and shown to improve performance in ambiguous/non-Markov environments.