Data processing method and device, electronic equipment and storage medium

Abstract

The invention provides a data processing method and device, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence, in particular to the technical field of deep learning. According to the scheme, the method comprises the steps of obtaining state data of an environment where a target object is located, inputting the state data into a strategy network of an enhancement model, sampling from an action set to obtain multiple actions corresponding to the state data, inputting the multiple actions and the state data into a guide network of the enhancement model, and outputting a target matching degree between each action and the state data, and according to the target matching degree of each action, determining a target action of the target object from the plurality of actions obtained by sampling. The subsequent processing efficiency is improved by sampling the multiple actions from the action set output by the strategy network, the state data and the multiple actions are combined to be input into the guide network, the target matching degree corresponding to each action is calculated, the target matching degree indicates the higher relevance between each action and the state data, and the action matching efficiency is improved. Therefore, the accuracy of target action determination is improved.

Description

technical field [0001] The present disclosure relates to the technical field of artificial intelligence, in particular to the technical field of deep learning, and in particular to a data processing method, device, electronic device, and storage medium. Background technique [0002] In recent years, reinforcement learning has been applied in many fields, such as games, robots, recommendation systems, etc. However, training a reinforcement learning model is time-consuming, because the reinforcement learning model needs to interact with the environment a lot during the training process to determine the matching actions, and these costs are high. At the same time, the simple exploration strategy slows down the learning speed of the model and even causes the model to make actions that are harmful to the environment. Therefore, how to improve the accuracy of action determination is a technical problem to be solved urgently. Contents of the invention [0003] The disclosure pr...

AI Technical Summary

Problems solved by technology

However, training a reinforcement learning model is time-consuming, because the reinforcement learning model needs to interact with the environment a lot during the training process to determine the matching actions, and these costs are high

At the same time, the simple exploration strategy slows down the learning speed of the model and even causes the model to make actions that are harmful to the environment

Images