DeepAI AI Chat
Log In Sign Up

Modeling Human Understanding of Complex Intentional Action with a Bayesian Nonparametric Subgoal Model

by   Ryo Nakahashi, et al.

Most human behaviors consist of multiple parts, steps, or subtasks. These structures guide our action planning and execution, but when we observe others, the latent structure of their actions is typically unobservable, and must be inferred in order to learn new skills by demonstration, or to assist others in completing their tasks. For example, an assistant who has learned the subgoal structure of a colleague's task can more rapidly recognize and support their actions as they unfold. Here we model how humans infer subgoals from observations of complex action sequences using a nonparametric Bayesian model, which assumes that observed actions are generated by approximately rational planning over unknown subgoal sequences. We test this model with a behavioral experiment in which humans observed different series of goal-directed actions, and inferred both the number and composition of the subgoal sequences associated with each goal. The Bayesian model predicts human subgoal inferences with high accuracy, and significantly better than several alternative models and straightforward heuristics. Motivated by this result, we simulate how learning and inference of subgoals can improve performance in an artificial user assistance task. The Bayesian model learns the correct subgoals from fewer observations, and better assists users by more rapidly and accurately inferring the goal of their actions than alternative approaches.


page 1

page 2

page 3

page 4


Modeling Human Inference of Others' Intentions in Complex Situations with Plan Predictability Bias

A recent approach based on Bayesian inverse planning for the "theory of ...

Theory of Minds: Understanding Behavior in Groups Through Inverse Planning

Human social behavior is structured by relationships. We form teams, gro...

Procedure Planning in Instructional Videosvia Contextual Modeling and Model-based Policy Learning

Learning new skills by observing humans' behaviors is an essential capab...

Modeling human intention inference in continuous 3D domains by inverse planning and body kinematics

How to build AI that understands human intentions, and uses this knowled...

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

Inferring intent from observed behavior has been studied extensively wit...

Investigating the Combination of Planning-Based and Data-Driven Methods for Goal Recognition

An important feature of pervasive, intelligent assistance systems is the...

Humans decompose tasks by trading off utility and computational cost

Human behavior emerges from planning over elaborate decompositions of ta...