Method and server for training machine learning algorithm for ranking objects

Abstract

Method and server for training a Machine Learning Algorithm (MLA) for ranking objects in response to a query are disclosed. The training includes use of a ranking quality metric function that is one of a flat and a discontinuous function to determine a performance score of the MLA. The method includes generating relevance scores for a set of training objects based on data associated with the set of training objects and a training query, generating noise-induced relevance scores for the set of training objects by combining the relevance scores and noise values, generating the performance score for the MLA based on the noise-induced relevance scores, determining a policy gradient value for adjusting relevance scores to be generated by the MLA for the in-use objects in response to the in-use query, and applying the policy gradient value for training the MLA to rank in-use objects in response to an in-use query.