ICLR 2018workshop210 citations

Investigating Human Priors for Playing Video Games

Rachit Dubey, Pulkit Agrawal, Deepak Pathak, Thomas L. Griffiths, Alexei A. Efros

Abstract

What makes humans so good at solving seemingly complex video games? Unlike computers, humans bring in a great deal of prior knowledge about the world, enabling efficient decision making. This paper investigates the role of human priors for solving video games. Given a sample game, we conduct a series of ablation studies to quantify the importance of various priors. We do this by modifying the video game environment to systematically mask different types of visual information that could be used by humans as priors. We find that removal of some prior knowledge causes a drastic degradation in the speed with which human players solve the game, e.g. from 2 minutes to over 20 minutes. Furthermore, our results indicate that general priors, such as the importance of objects and visual consistency, are critical for efficient game-play.

Prior knowledgeReinforcement learningCognitive Science
BibTeX
@misc{
dubey2018investigating,
title={Investigating Human Priors for Playing Video Games},
author={Rachit Dubey and Pulkit Agrawal and Deepak Pathak and Thomas L. Griffiths and Alexei A. Efros},
year={2018},
url={https://openreview.net/forum?id=Hk91SGWR-},
}
Investigating Human Priors for Playing Video Games · ICLR 2018