A system, method, and apparatus for identifying optimal or near optimal complex stimulation waveforms for a neurostimulator device or neuromodulation device are disclosed. An example method includes using a dueling bandits algorithm with correlation among stimulation arms to select a batch of stimulation arms for sequential application to a patient during a therapy session. Each of the stimulation arms specifies complex stimulation waveform parameter values. Feedback from applying the stimulation arms to the patient is recorded and used to update feedback reward values corresponding to at least some of the stimulation arms using a stimulation arm correlation index. A second batch of stimulations arms is selected based upon the updated feedback reward values and applied to a patient. The method is iteratively repeated over a number of therapy sessions until an optimal or near optimal batch of stimulation arms (defining complex stimulation waveforms) is determined.