Investigating Human Priors for Playing Video Games
This work addresses the problem of understanding human cognitive advantages in video games for AI and cognitive science, but it is incremental as it quantifies known priors rather than introducing new methods.
The paper investigates the role of human priors in solving video games by conducting ablation studies that mask visual information, finding that removal of certain priors drastically degrades performance, e.g., increasing solving time from 2 minutes to over 20 minutes.
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/