: This paper proposes an improved Experience-Weighted Attraction (EWA) selection algorithm with channel handoff scheme in order to meet the practical requirement for Cognitive Radio (CR) application. In further research, sensitivity and stability verification is conducted by focusing on the comparison with Q learning algorithm after the establishment of a wireless simulation space with time slot sequences that extremely imitates real Cognitive Radio environments. The emulation results show that channel selection strategy with EWA learning has more advantageous performance. Copyright © 2014 IFSA Publishing, S. L.