Where Do You Think You're Going?: Inferring Beliefs about Dynamics from Behavior

TL;DR

This paper introduces a novel approach to inferring human intent by modeling suboptimal behavior as stemming from incorrect beliefs about environment dynamics, improving accuracy in shared autonomy and preference inference.

Contribution

The paper proposes a new method that infers internal beliefs about environment dynamics from observed behavior, enhancing intent prediction beyond traditional reward-based models.

Findings

More accurate modeling of human intent in simulations.

Effective in shared autonomy assistance scenarios.

Improves inference of human preferences.

Abstract

Inferring intent from observed behavior has been studied extensively within the frameworks of Bayesian inverse planning and inverse reinforcement learning. These methods infer a goal or reward function that best explains the actions of the observed agent, typically a human demonstrator. Another agent can use this inferred intent to predict, imitate, or assist the human user. However, a central assumption in inverse reinforcement learning is that the demonstrator is close to optimal. While models of suboptimal behavior exist, they typically assume that suboptimal actions are the result of some type of random noise or a known cognitive bias, like temporal inconsistency. In this paper, we take an alternative approach, and model suboptimal behavior as the result of internal model misspecification: the reason that user actions might deviate from near-optimal actions is that the user has an incorrect set of beliefs about the rules -- the dynamics -- governing how actions affect the environment. Our insight is that while demonstrated actions may be suboptimal in the real world, they may actually be near-optimal with respect to the user's internal model of the dynamics. By estimating these internal beliefs from observed behavior, we arrive at a new method for inferring intent. We demonstrate in simulation and in a user study with 12 participants that this approach enables us to more accurately model human intent, and can be used in a variety of applications, including offering assistance in a shared autonomy framework and inferring human preferences.