Investigating Human Priors for Playing Video Games

TL;DR

This study explores how human prior knowledge influences performance in video games by systematically removing visual cues, revealing that certain priors are crucial for efficient gameplay.

Contribution

It provides a systematic analysis of the role of human priors in video game solving, highlighting which types of prior knowledge are most critical.

Findings

Removing key priors significantly slows human gameplay.

General priors like object importance are vital for efficiency.

Visual masking impacts performance drastically.

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/