Computational method for training a meta-taught evolutionary strategy black box optimization classifier. The method includes receiving one or more training functions and one or more initial Metalern parameters of the meta-taught evolutionary strategy black box optimization classifier. The method further includes sampling a sampled objective function from the one or more training functions and an initial average of the sampled objective function. The method also includes computing a set of T number of means by running the meta-taught evolutionary strategy black box optimization classifier on the sampled objective function using the initial mean for a number T of steps in t = 1, ..., T. The method also includes computing a loss function from the set of T-numbers of means. The method further includes updating the one or more initial Metalern parameters of the meta-taught evolutionary strategy black box optimization classifier in response to a characteristic of the loss function.
展开▼