Method and apparatus for displaying page to user through reinforcement learning

Abstract

Implementations of this specification provide a method and an apparatus for obtaining a display policy through reinforcement learning techniques. The display policy can be used to select particular page layouts to present to a user. The method includes the following: obtaining user features of a first user in response to a request for accessing a first page by the first user; selecting, according to a display policy and based on the user features, a first page layout from a first plurality of candidate page layouts; displaying the first page to the first user with the first page layout; obtaining operation information of the first user on the first page with the first page layout, and determining a reward score for current page display based on the operation information; and updating the display policy for displaying pages by using a reinforcement learning algorithm based at least on the reward score.