Abstract: A method for intelligently controlling a mechanical arm includes building a twin model of a mechanical arm, and extracting a state parameter and an action parameter corresponding to task characteristics from the twin model; determining a reward function corresponding to the task characteristics; training a twin delayed deep deterministic policy gradient (TD3) reinforcement learning model; simulating in the twin model based on a physical state parameter of the mechanical arm by using the TD3 reinforcement learning model, to obtain a controllable parameter; and controlling the mechanical arm to execute a corresponding task by using the controllable parameter. The TD3 reinforcement learning model is built based on the state parameter and the action parameter corresponding to the task characteristics and the reward function corresponding to the task characteristics, which can adapt to a dynamically changing environment and requirements for multiple tasks.

Abstract: A model training method and apparatus, a storage medium, and a device, relating to the field of artificial intelligence (AI) technologies are provided. The method includes: obtaining a plurality of training samples, each training sample including an interaction screen and an action label, the action label indicating an interaction action adopted by a character object in the interaction screen; extracting features from the interaction screens included in the plurality of training samples, and performing clustering according to the extracted features, to obtain a clustering result; determining at least one key sample from the plurality of training samples according to the clustering result; and setting a weight for each training sample, and updating a network parameter of a deep network based on the plurality of training samples with the weights, the weight of each key sample being greater than the weight of another sample in the plurality of training samples.