按年被提到
20182019 · 1 次2026
强化学习与智能体›博弈与游戏 AI·arXiv:1802.10217 · cs.AI

Investigating Human Priors for Playing Video Games

Rachit Dubey, Pulkit Agrawal, Deepak Pathak, Thomas L. Griffiths, Alexei A. Efros · 2018
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2019-10-18 · 最近 2020-05-22
2不同的人
2活跃月份
2讨论串
100被引(OpenAlex)
arXiv 摘要(候选层不写导读)

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/

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论QuadmasterXLII · 2019-10

“This[1] paper does an excellent job gradually removing cultural priors from a simple videogame, and measuring the extent to which human and computer performance degrade. Their conclusion is that human ability to learn games fast depends on our ability to map them to real world concepts. Would it be permitted for entrants in your contest to pretrain on som…”

Machines Beat Humans on a Reading Test原评论 ↗
评论ki28iukgvdru · 2020-05

“Indeed. Some work has actually been done to try to quantify how important various types of human prior knowledge are for learning video games: https://arxiv.org/pdf/1802.10217.pdf”

Pac-Man recreated with a GAN trained on 50k game episodes原评论 ↗