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.