How XCS can prevent misdistinguishing rule accuracy
Masaya Nakata, Will Neil Browne · Proceedings of the Genetic and Evolutionary Computation Conference Companion · 2019
On the XCS classifier system, an ideal assumption in the latest XCS learning theory means that it is impossible for XCS to distinguish accurate rules from any other rules with 100% success rate in practical use. This paper presents a preliminary work to remove this assumption. Furthermore, it reveals a dilemma in setting a crucial XCS parameter. That is, to guarantee 100% success rate, the learning rate should be greater than 0.5. However, a rule fitness updated with such a high learning rate would not converge to its true value so rule discovery would not act properly.