The invention discloses a behavior control strategy learning method and device, computer equipment and a storage medium. The method comprises the steps of sampling a demonstration behavior data segment comprising at least two demonstration behavior data from a demonstration behavior data sequence; setting initial state information of each joint of the target object simulated in the physical simulator according to the demonstration behavior data segment, and determining acting force data of each joint of the target object by utilizing a to-be-trained neural network model; controlling the motionof each joint of the target object simulated in the physical simulator, so that the physical simulator simulates a simulation behavior data sequence of the target object based on the set action behavior limiting characteristics; determining an action behavior difference degree according to the demonstration behavior data and the simulation behavior data; and based on the action behavior difference degree, optimizing the neural network model until an optimization target is achieved. The scheme of the invention is beneficial to demonstrating that the learned object generates the extended actionbehavior based on the demonstration action.