For this purpose, Q-learning based Failure Detection and Self-Recovery (FDSR) algorithm is proposed in this study.
(FDSR) algorithm assumes a heterogeneous MRS with m robots ([R.sub.j], j = 1, ..., m) having the ability to do n different types of tasks ([T.sub.i], i = 1, ..., n).
To show the effectiveness of the proposed algorithm, experiments are realized for three methods named as no-L, only-QL and FDSR. The first method, no-L, represents the no learning case with usual bidding strategy.
FDSR method aims to find out the environmental changes and to specify whether these are permanent or not.