Interactive POMDP Lite: Towards Practical Planning to Predict and Exploit Intentions for Interacting with Self-Interested Agents
This addresses the problem of practical planning for interacting with self-interested agents, such as humans, in multi-agent systems, representing an incremental improvement over existing methods.
The paper tackles the challenge of efficient planning in non-cooperative multi-agent systems with self-interested agents by developing an intention-aware planning framework that predicts and exploits agent intentions, showing that performance losses are linearly bounded by prediction error and achieving better, more robust performance than state-of-the-art algorithms in empirical evaluations.
A key challenge in non-cooperative multi-agent systems is that of developing efficient planning algorithms for intelligent agents to interact and perform effectively among boundedly rational, self-interested agents (e.g., humans). The practicality of existing works addressing this challenge is being undermined due to either the restrictive assumptions of the other agents' behavior, the failure in accounting for their rationality, or the prohibitively expensive cost of modeling and predicting their intentions. To boost the practicality of research in this field, 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. We show that the performance losses incurred by the resulting planning policies are linearly bounded by the error of intention prediction. Empirical evaluations through a series of stochastic games demonstrate that our policies can achieve better and more robust performance than the state-of-the-art algorithms.