Inverse Reinforcement Learning Approach for Elicitation of Preferences in Multi-objective Sequential Optimization

It is crucial to know which criterion should be focused on, in a multi-objective decision making context, to select the best alternative from the multiple Pareto optimal solutions. However, in general, it is hard for the decision maker to express his/her own preference order for each criterion. In this study, we propose a preference elicitation method to estimate relative importance in terms of weights for each criterion by observing his/her processes of decision making. This method would make expert's preference elicited, and contribute at an important decision making point, such as urban planning.