Active Preference Elicitation for Planning

Mayukh Das, Md Rakibul Islam, Janardhan Rao Doppa, Dan Roth, Sriraam Natarajan

Abstract: We consider the problem of actively eliciting preferences from a human by a planning system. While prior work in planning have explored the use of domain knowledge and preferences, they assume that the knowledge must be provided before the planner starts the planning process. Our work is in building more collaborative systems where a system can solicit advice as needed. We verify empirically that this approach lead to faster and better solutions, while reducing the burden on the human expert.