According to artificial intelligence studies, goal-based and utility-based agents can select an action to attain a desired outcome. The goal-based agent sets a specific goal regardless of its utility at first, and selects the action that leads to that goal (goal-based action selection). The utility-based agent compares the utilities of different possible outcomes, and selects the action that causes the outcome with the highest utility (utility-based action bias). The medial prefrontal cortex is involved in implementing the goal-based action selection and the striatum is involved in implementing the utility-based action bias. Goal-based action selection may be temporarily dominant over the utility-based action bias in a new environment, whereas the utility-based action bias becomes dominant after acquisition of action utilities in the environment. This transition of dominance between the two decision systems may be enhanced by a reference-point shift based on the goal-setting process during goal-based action selection.