Training method of action control model, related device and storage medium

Abstract

The invention discloses a training method of an action control model, and the method is applied to the field of artificial intelligence, and specifically comprises the steps: obtaining first state data corresponding to a target role from a to-be-trained segment; based on the first state data, obtaining an action prediction value through a to-be-trained action control model; determining action dataof the target role according to the action prediction value and the M groups of offset parameter sets; and updating model parameters of a to-be-trained action control model according to the first state data and the action data. The invention further discloses a model training device and a storage medium. According to the method, the predicted value of the joint can be converted into the reasonable motion range of the joint, manual adjustment is not needed, the model training efficiency can be improved, the model training effect can also be improved, and therefore the animation effect of character performance is better.

Description

technical field

[0001] The present application relates to the field of artificial intelligence, and in particular to a training method for an action control model, a related device and a storage medium. Background technique

[0002] Animation effects such as movies and game applications are becoming more and more realistic as machine learning technology continues to develop. Whether it is in a movie or a game application, an important goal for character animation is to better integrate the current self state and the current environment state to make it produce more natural movements.

[0003] In order to better integrate the character into the real physical environment, a method of character movement training based on a physics engine can be used. That is, the key frame data is obtained as a reference action. In the training platform based on the physics engine, the character is trained by means of reinforcement learning. During the process of reinforcement learning, each j...

Images