A dynamic niche-based self-organizing learning algorithm (DNSLA) was proposed in this paper. The dynamic learning mechanism based on 0-1 coding method was carried out, and the individuals involved in this algorithm were able to adapt to the dynamic environments through active learning, which was different from the passive adaptive search strategy in traditional evolutionary algorithms. As a result of self-organizing learning and friendly interaction with the environments, DNSLA was more robust to adapt to the dynamic problems, and it was able to accurately detect the slight changes of the environments and track the extreme points in the solution domain. A series of dynamic simulation tests for comparative experiments showed that, even in the turbulent environments, DNSLA was still able to perform friendly interactive learning with the dynamic environments. DNSLA showed a strong robustness in the comparative experiments, whose dynamic search capabilities were far superior to other search methods.