Özet:

Problem solving is one of renown artificial intelligence fields, which has kept attracting research for decades. Swarm intelligence is recognised as the family of the state-of-art approaches in problem solving, which attracted much research attention for the enduring problems. The main challenge appears to be in the speed of algorithmic approximation where many approaches were proposed to accelerate approximation avoiding local optima. Recent research demonstrates that inefficiencies in search procedures can be side-stepped using the experiences gained while search is undergoing utilising machine learning approaches. Reinforcement learning is a success-proven approach for online learning, especial when training data is not available upfront. In this paper, we overview the usefulness of machine learning in performance improvement of artificial bee colony algorithms in solving combinatorial optimisation problems. Furthermore, we demonstrate how reinforcement learning approaches facilitate swarm intelligence algorithms to gain experience for immediate and later use to build capable and powerful operator selection schemes, which help improve efficiency of swarm intelligence problem solvers

Anahtar Kelimeler: