A Bayesian-Symbolic Approach to Reasoning and Learning in Intuitive Physics
Authors
Authors
- Akash Srivastava
- Dan Gutfreund
- Joshua Tenenbaum
- Kai Xu
- Felix Anthony Sosa
- Tomer Ullman
- Charles Sutton
Authors
- Akash Srivastava
- Dan Gutfreund
- Joshua Tenenbaum
- Kai Xu
- Felix Anthony Sosa
- Tomer Ullman
- Charles Sutton
Published on
12/14/2021
Categories
Humans can reason about intuitive physics in fully or partially observed environments even after being exposed to a very limited set of observations. This sample-efficient intuitive physical reasoning is considered a core domain of human common sense knowledge. One hypothesis to explain this remarkable capacity, posits that humans quickly learn approximations to the laws of physics that govern the dynamics of the environment. In this paper, we propose a Bayesian-symbolic framework (BSP) for physical reasoning and learning that is close to human-level sample-efficiency and accuracy. In BSP, the environment is represented by a topdown generative model of entities, which are assumed to interact with each other under unknown force laws over their latent and observed properties. BSP models each of these entities as random variables, and uses Bayesian inference to estimate their unknown properties. For learning the unknown forces, BSP leverages symbolic regression on a novel grammar of Newtonian physics in a bilevel optimization setup. These inference and regression steps are performed in an iterative manner using expectation-maximization, allowing BSP to simultaneously learn force laws while maintaining uncertainty over entity properties. We show that BSP is more sample-efficient compared to neural alternatives on controlled synthetic datasets, demonstrate BSP’s applicability to real-world common sense scenes and study BSP’s performance on tasks previously used to study human physical reasoning.
This paper has been published at NeurIPS 2021.
Please cite our work using the BibTeX below.
@inproceedings{
xu2021a,
title={A Bayesian-Symbolic Approach to Reasoning and Learning in Intuitive Physics},
author={Kai Xu and Akash Srivastava and Dan Gutfreund and Felix Anthony Sosa and Tomer Ullman and Joshua B. Tenenbaum and Charles Sutton},
booktitle={Advances in Neural Information Processing Systems},
editor={A. Beygelzimer and Y. Dauphin and P. Liang and J. Wortman Vaughan},
year={2021},
url={https://openreview.net/forum?id=WN8ChCARq2}
}