Investigating Human Priors for Playing Video Games

Rachit Dubey, Pulkit Agrawal, Deepak Pathak, Tom Griffiths, Alexei Efros
Proceedings of the 35th International Conference on Machine Learning, PMLR 80:1349-1357, 2018.

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 on human performance. 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. Videos and the game manipulations are available at https://rach0012.github.io/humanRL_website/

Cite this Paper

BibTeX
@InProceedings{pmlr-v80-dubey18a, title = {Investigating Human Priors for Playing Video Games}, author = {Dubey, Rachit and Agrawal, Pulkit and Pathak, Deepak and Griffiths, Tom and Efros, Alexei}, booktitle = {Proceedings of the 35th International Conference on Machine Learning}, pages = {1349--1357}, year = {2018}, editor = {Dy, Jennifer and Krause, Andreas}, volume = {80}, series = {Proceedings of Machine Learning Research}, month = {10--15 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v80/dubey18a/dubey18a.pdf}, url = {https://proceedings.mlr.press/v80/dubey18a.html}, 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 on human performance. 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. Videos and the game manipulations are available at https://rach0012.github.io/humanRL_website/} }
Endnote
%0 Conference Paper %T Investigating Human Priors for Playing Video Games %A Rachit Dubey %A Pulkit Agrawal %A Deepak Pathak %A Tom Griffiths %A Alexei Efros %B Proceedings of the 35th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2018 %E Jennifer Dy %E Andreas Krause %F pmlr-v80-dubey18a %I PMLR %P 1349--1357 %U https://proceedings.mlr.press/v80/dubey18a.html %V 80 %X 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 on human performance. 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. Videos and the game manipulations are available at https://rach0012.github.io/humanRL_website/
APA
Dubey, R., Agrawal, P., Pathak, D., Griffiths, T. & Efros, A.. (2018). Investigating Human Priors for Playing Video Games. Proceedings of the 35th International Conference on Machine Learning, in Proceedings of Machine Learning Research 80:1349-1357 Available from https://proceedings.mlr.press/v80/dubey18a.html.

Related Material