Work

Showing versus Doing: Teaching by Demonstration

Year: 2026

Type: preprint

Abstract: People often learn from others' demonstrations, and inverse reinforcement learning (IRL) techniques have realized this capacity in machines. In contrast, teaching by demonstration has been less well studied computationally. Here, we develop a Bayesian model for teaching by demonstration. Stark differences arise when demonstrators are intentionally teaching (i.e. showing) a task versus simply performing (i.e. doing) a task. In two experiments, we show that human participants modify their teaching behavior consistent with the predictions of our model. Further, we show that even standard IRL algorithms benefit when learning from showing versus doing.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.14004

Authors: Ho, Mark K., Littman, Michael L., MacGlashan, James, Cushman, Fiery, Austerweil, Joseph L.

Institutions: Brown University, Harvard University, University of Wisconsin–Madison

Language: English

Topic: Reinforcement Learning in Robotics

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

SDG: Quality education

Open Access status: green

Funders: National Science Foundation, Defense Advanced Research Projects Agency, Office of Naval Research