Intention-Aware Planning under Uncertainty for Interacting with Self-Interested, Boundedly Rational Agents (Extended Abstract)
Trong Nghia Hoang, Kian Hsiang Low · 2012
A key challenge in non-cooperative multi-agent systems is that of developing ecient planning algorithms for intelligent agents to perform eectively among boundedly rational 1 , self-interested (i.e., non-cooperative) agents (e.g., humans). To address this challenge, we investigate how intention prediction can be eciently exploited and made practical in planning, thereby leading to ecient intention-aware planning frameworks capable of predicting the intentions of other agents and acting optimally with respect to their predicted intentions.