An abstraction agorithm for genetics-based reinforcement learning
Will Neil Browne, Dan Scott · 2005
Abstraction is a higher order cognitive ability that facilitates the production of rules that are independent of their associations. Experience from real-world data-mining has shown the need for such higher level rules. The game of Connect 4 is both multistep and complex, so standard Q-learning and Learning Classifier Systems perform poorly. The introduction of a novel Abstraction algorithm into an LCS is shown to improve performance in the evolution of playing strategies.