Reinforcement learning studies how an agent makes decisions through the interaction with the unknown environment, its core is to learn the policy. The action selection of traditional policy model mainly depends on state perception, historical memory and model parameters, which are difficult to control. However, when human fulfill a task, they usually make decisions according to their own intention or motivation. Inspired by the human decision-making mechanism, in order to make the behavior selection mechanism controllable and enable the agent to choose the action according to the intention, this paper proposed to incorporate the intention variable to the policy model and obtain an intention motivated reinforcement learning method. More specifically, the proposed method maximized the mutual information between the intention variables and the actions, so that the policy could select the action related to the intention variable. Finally, the effectiveness of the proposed intention-motivated control was demonstrated through the complex Mujoco environment in simulated robot control task.

[2022-06-17] Accepted Paper /doc/2022.03.0168/v1

[2022-11-05] Printed Article /doc/2022.03.0168/v2