Intention-aware planning under uncertainty for interacting with self-interested, boundedly rational agents

A key challenge in non-cooperative multi-agent systems is that of developing efficient planning algorithms for intelligent agents to perform effectively among boundedly rational, self-interested (i.e., non-cooperative) agents (e.g., humans). To address this challenge, we investigate how intention prediction can be efficiently exploited and made practical in planning, thereby leading to efficient intention-aware planning frameworks capable of predicting the intentions of other agents and acting optimally with respect to their predicted intentions.