Inferring the Future by Imagining the Past

Kartik Chandra, Tony Chen, Tzu-Mao Li, Jonathan Ragan-Kelley, Joshua B. Tenenbaum

Keywords: Theory of mind, Monte Carlo, inverse planning

TL;DR: How to infer an agent's goal from a static snapshot of its current state, by Monte Carlo sampling possible trajectories

Abstract:

A single panel of a comic book can say a lot: it shows not only where characters currently are, but also where they came from, what their motivations are, and what might happen next. More generally, humans can often infer a complex sequence of past and future events from a *single snapshot image* of an intelligent agent.

Building on recent work in cognitive science, we offer a Monte Carlo algorithm for making such inferences. Drawing a connection to Monte Carlo path tracing in computer graphics, we borrow ideas that help us dramatically improve upon prior work in sample efficiency. This allows us to scale to a wide variety of challenging inference problems with only a handful of samples. It also suggests some degree of cognitive plausibility, and indeed we present human subject studies showing that our algorithm matches human intuitions in a variety of domains that previous methods could not scale to.

Submission Number: 15