Training method of reinforced learning model, node, system and storage medium

Abstract

The invention discloses a training method of a reinforced learning model, a node, a system and a storage medium. The training method comprises the steps of acquiring local data by a training node, andinputting the local data as a sample into a first neural network for training, thereby obtaining a first optimal sub-objective function; receiving a parameter from a second optimal sub-objective function of a neighboring node; introducing the parameter of the second optimal sub-objective function into the first optimal sub-objective function for obtaining a second optimal sub-objective function;and performing weighted averaging operation on the first optimal sub-objective function and the second sub-objective function, thereby obtaining an optimal objective function. Through the method, a data leakage problem in the training process of the reinforced leaning model can be settled.

Description

technical field [0001] The present application relates to the technical field of machine learning, in particular to a training method, node, system and storage medium of a reinforcement learning model. Background technique [0002] Reinforcement learning algorithm is a machine learning algorithm that maps from the state of the environment to actions, so that the cumulative reward value obtained by the action from the environment is the largest. With the evolution of computing power and algorithms, reinforcement learning has been widely used in robot control, cluster management, and network traffic control. [0003] However, a large amount of data is required to train the reinforcement learning algorithm model, which also brings hidden dangers to data leakage. Especially in the training of reinforcement learning algorithms in open network clusters, there are even more hidden concerns about the direct leakage of training data and the leakage of training data indirectly derive...

AI Technical Summary

Problems solved by technology

[0003] However, a large amount of data is required to train the reinforcement learning algorithm model, which also brings hidden dangers to data leakage.

Especially in the training of reinforcement learning algorithms in open network clusters, the direct leakage of training data and the leakage of training data indirectly derived from the trained model are even more worrying.

Images