Robot control method and device, storage medium and equipment

The invention discloses a robot control method and device, a storage medium and equipment, and the method comprises the steps: obtaining a motion target point and an expected motion state, selecting a reinforcement learning model corresponding to the expected motion state from at least one reinforcement learning model which is trained in advance, and taking the selected reinforcement learning model as an application model, inputting the current motion state of the robot and the motion target point into the application model, enabling the application model to determine the reward score of each selectable motion instruction according to the current motion state, the motion target point and each selectable motion instruction, and determining a target motion instruction in each selectable motion instruction according to the reward score, the robot is controlled to move according to the target motion instruction, the reinforcement learning model is utilized, the robot is controlled to move in different expected mo