@inproceedings{1491dcf723674afa8ccf0feba5f511bd,
title = "Active physical inference via reinforcement learning",
abstract = "When encountering unfamiliar physical objects, children and adults often perform structured interrogatory actions such as grasping and prodding, so revealing latent physical properties such as masses and textures. However, the processes driving and supporting these curious behaviors are still largely mysterious. In this paper, we develop and train an agent able to actively uncover latent physical properties such as the mass and force of objects in a simulated physical “micro-world'. Concretely, we used a simulation-based-inference framework to quantify the physical information produced by observation and interaction with the evolving dynamic environment. We used model-free reinforcement learning algorithm to train an agent to implement general strategies for revealing latent physical properties. We compare the behaviors of this agent to the human behaviors observed in a similar task.",
keywords = "active learning, physical simulation, probabilistic inference, reinforcement learning",
author = "Shuaiji Li and Yu Sun and Sijia Liu and Tianyu Wang and Gureckis, {Todd M.} and Bramley, {Neil R.}",
note = "Publisher Copyright: {\textcopyright} Cognitive Science Society: Creativity + Cognition + Computation, CogSci 2019.All rights reserved.; 41st Annual Meeting of the Cognitive Science Society: Creativity + Cognition + Computation, CogSci 2019 ; Conference date: 24-07-2019 Through 27-07-2019",
year = "2019",
language = "English (US)",
series = "Proceedings of the 41st Annual Meeting of the Cognitive Science Society: Creativity + Cognition + Computation, CogSci 2019",
publisher = "The Cognitive Science Society",
pages = "2126--2132",
booktitle = "Proceedings of the 41st Annual Meeting of the Cognitive Science Society",
}